© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 12848
    Prev
    Next
    INDEX
    Explanations

    positive and negative relationships between different elements

    oai_token-act-pair · gpt-3.5-turbo

    words that describe contrasting qualities or comparative scenarios, specifically highlighting positive and negative aspects

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    0
    +0.17
    0.6%
    187
    +0.17
    0.6%
    200
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    200
    +0.17
    0.05
    711
    +0.17
    0.04
    187
    +0.15
    0.05
    Negative Logits
    adr
    -1.15
    arers
    -1.02
    BuyableInstoreAndOnline
    -1.01
    ITNESS
    -1.01
    neys
    -0.98
    ngth
    -0.97
    conservancy
    -0.96
    soDeliveryDate
    -0.96
    resp
    -0.95
    tower
    -0.94
    POSITIVE LOGITS
     reinforcement
    1.12
     affirm
    1.04
     outcome
    1.02
     affirmation
    1.02
     spiral
    0.98
     impact
    0.98
     vib
    0.94
     feedback
    0.93
     infinity
    0.91
     Scotia
    0.90
    Activations Density 0.921%

    No Known Activations