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. 40178
    Prev
    Next
    INDEX
    Explanations

    explanations or descriptions and instances of a concept or topic within context

    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
    +0.31
    1.5%
    38
    +0.10
    0.5%
    395
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    344
    +0.31
    0.15
    426
    +0.10
    0.10
    227
    +0.10
    0.06
    Negative Logits
    ©¶æ
    -0.71
    buster
    -0.70
    ufact
    -0.67
    erate
    -0.65
    assisted
    -0.64
    istan
    -0.63
    enment
    -0.62
    livion
    -0.62
    ħĭ
    -0.61
    breaker
    -0.60
    POSITIVE LOGITS
     reasons
    0.96
     ways
    0.90
     similarities
    0.90
     variations
    0.86
     unanswered
    0.85
     occasions
    0.84
     conflicting
    0.81
     possibilities
    0.80
     advantages
    0.80
     opportunities
    0.77
    Activations Density 10.569%

    No Known Activations