© 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
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 39995
    Prev
    Next
    INDEX
    Explanations

    references to different cities and sports teams, particularly the Cincinnati Bengals

    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
    484
    +0.11
    0.6%
    494
    +0.11
    0.5%
    566
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.21
    288
    +0.11
    0.20
    494
    +0.10
    0.11
    Negative Logits
    bes
    -0.72
     Cheong
    -0.71
    uckland
    -0.69
    ieth
    -0.68
    uate
    -0.68
    pring
    -0.68
    eting
    -0.68
     Lauder
    -0.65
    uable
    -0.65
    clinton
    -0.65
    POSITIVE LOGITS
     Reds
    0.92
     Bengals
    0.91
    xual
    0.79
    incinn
    0.78
    cone
    0.71
    incinnati
    0.66
    ĸļ
    0.65
    hedral
    0.64
     XIII
    0.64
     Bengal
    0.64
    Activations Density 7.124%

    No Known Activations