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 Local
    5. 6-RES_SCL-AJT
    6. 40188
    Prev
    Next
    INDEX
    Explanations

    JavaScript code snippets

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    545
    +0.07
    0.5%
    502
    +0.07
    0.5%
    414
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.07
    0.20
    160
    +0.07
    0.17
    598
    +0.07
    0.04
    Negative Logits
     Cosponsors
    -0.57
    ãĥ³ãĤ¸
    -0.53
    Maria
    -0.47
    jab
    -0.46
    pedia
    -0.44
    wana
    -0.43
     Glover
    -0.42
    ħĭ
    -0.42
     Zup
    -0.41
     Quote
    -0.41
    POSITIVE LOGITS
    ){
    0.61
    >)
    0.55
    ):
    0.54
    ())
    0.53
    ++)
    0.51
     ())
    0.48
    ])
    0.47
     &&
    0.47
    );
    0.46
    ,)
    0.44
    Activations Density 7.444%

    No Known Activations