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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 40430
    Prev
    Next
    INDEX
    Explanations

    content related to biology, biological sciences, and specific biology-related terms such as genetics, anatomy, and medical conditions

    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
    447
    +0.13
    0.7%
    269
    +0.13
    0.7%
    575
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.13
    0.14
    138
    +0.13
    0.12
    26
    +0.09
    0.11
    Negative Logits
    heed
    -0.63
    engers
    -0.62
    naire
    -0.60
    igmat
    -0.60
    ership
    -0.58
    ewitness
    -0.57
    adra
    -0.56
    ription
    -0.56
    enger
    -0.54
    plings
    -0.54
    POSITIVE LOGITS
     biologists
    0.67
    sonian
    0.67
    alogy
    0.67
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.66
     biologist
    0.66
     biology
    0.65
     Laboratory
    0.64
     sciences
    0.62
    biology
    0.61
    gon
    0.57
    Activations Density 10.686%

    No Known Activations