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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 34366
    Prev
    Next
    INDEX
    Explanations

    information about American football games, players, and performances

    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
    373
    +0.12
    0.5%
    668
    +0.10
    0.5%
    325
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.12
    0.11
    442
    +0.10
    0.07
    323
    +0.10
    0.08
    Negative Logits
    ħĭ
    -0.85
     plur
    -0.80
     ageing
    -0.80
     paed
    -0.78
     ethnic
    -0.76
    hov
    -0.74
     redundancy
    -0.72
     coats
    -0.71
     insol
    -0.71
     organis
    -0.71
    POSITIVE LOGITS
     Pwr
    0.89
     misses
    0.80
     touchdown
    0.78
    phrase
    0.75
     FG
    0.73
    book
    0.73
    tackle
    0.72
    aways
    0.72
    calling
    0.72
    call
    0.72
    Activations Density 4.339%

    No Known Activations