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

    Neuronpedia

    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. 13384
    Prev
    Next
    INDEX
    Explanations

    phrases related to direction or movement involving leaving, going into, safety, or specific actions like drinking from a fountain

    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
    393
    +0.14
    0.5%
    608
    +0.13
    0.4%
    655
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.14
    0.15
    526
    +0.13
    0.00
    665
    +0.13
    0.12
    Negative Logits
    caster
    -1.11
    ounces
    -1.07
    soDeliveryDate
    -1.03
    BALL
    -1.03
    ricks
    -1.00
    chini
    -0.98
    estate
    -0.94
    natureconservancy
    -0.89
    etta
    -0.88
    shop
    -0.88
    POSITIVE LOGITS
     obscurity
    1.25
    pload
    1.23
     rubble
    1.15
     pasture
    1.08
     tears
    1.03
     avoid
    1.00
     disgrace
    0.99
     ashes
    0.98
     consolidate
    0.97
     unpop
    0.96
    Activations Density 2.980%

    No Known Activations