© 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. 6367
    Prev
    Next
    INDEX
    Explanations

    references to past events or actions

    oai_token-act-pair · gpt-3.5-turbo
    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
    706
    +0.19
    0.6%
    383
    +0.15
    0.5%
    99
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    706
    +0.19
    0.05
    383
    +0.15
    0.05
    175
    +0.15
    0.03
    Negative Logits
    ocol
    -1.08
    PsyNetMessage
    -1.06
    rals
    -1.05
    needs
    -1.02
    LESS
    -1.01
    LCS
    -0.98
    heses
    -0.98
    onga
    -0.98
    osis
    -0.98
    OG
    -0.97
    POSITIVE LOGITS
    handedly
    1.14
     employed
    1.02
     belonged
    1.02
     again
    1.01
     married
    0.99
     mill
    0.97
     departed
    0.97
     harb
    0.97
     disgruntled
    0.96
     disembark
    0.95
    Activations Density 0.454%

    No Known Activations