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. 4293
    Prev
    Next
    INDEX
    Explanations

    references to football players and team strategies

    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
    7
    +0.13
    0.6%
    289
    +0.11
    0.5%
    583
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.24
    683
    +0.11
    0.12
    288
    +0.11
    0.24
    Negative Logits
    hered
    -0.85
    bourg
    -0.84
    isSpecialOrderable
    -0.84
    ð
    -0.80
    falls
    -0.77
    ngth
    -0.77
    bery
    -0.77
    é¾įå
    -0.76
    urdue
    -0.75
    ushi
    -0.75
    POSITIVE LOGITS
    ially
    1.00
    er
    0.91
    ers
    0.84
    ials
    0.71
    eers
    0.70
    eer
    0.68
    ial
    0.67
    IAL
    0.65
     Neurolog
    0.65
     gearing
    0.64
    Activations Density 8.889%

    No Known Activations