Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 614
    Prev
    Next
    INDEX
    Explanations

    fast-paced action or events

    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
    620
    +0.15
    0.5%
    178
    +0.15
    0.5%
    422
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    422
    +0.15
    0.04
    271
    +0.15
    0.04
    128
    +0.14
    0.04
    Negative Logits
    pheus
    -1.15
    ignty
    -1.03
     Seym
    -1.01
    xual
    -1.00
    cules
    -1.00
     Hawth
    -0.98
    vironment
    -0.96
    iverpool
    -0.96
    ktop
    -0.93
     Contributions
    -0.93
    POSITIVE LOGITS
    idious
    1.81
     paced
    1.63
    ened
    1.52
    eners
    1.42
    ening
    1.21
    ener
    1.20
    nesses
    1.14
    cgi
    1.12
     asleep
    1.09
     lear
    1.07
    Activations Density 0.618%

    No Known Activations