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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 13921
    Prev
    Next
    INDEX
    Explanations

    sports predictions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    161
    +0.14
    0.5%
    208
    +0.13
    0.5%
    238
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    238
    +0.14
    0.05
    176
    +0.13
    0.04
    161
    +0.13
    0.04
    Negative Logits
    ÄŁ
    -1.09
    usercontent
    -1.00
    izoph
    -0.95
    videos
    -0.94
    swer
    -0.91
    stad
    -0.85
    edi
    -0.84
    rose
    -0.84
    agna
    -0.84
    wives
    -0.83
    POSITIVE LOGITS
     Boise
    0.96
     record
    0.89
     aggregate
    0.89
     Indianapolis
    0.88
     undefeated
    0.87
     combo
    0.87
     career
    0.86
     blues
    0.85
    ISM
    0.85
     Incarn
    0.83
    Activations Density 0.556%

    No Known Activations