© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 6079
    Prev
    Next
    INDEX
    Explanations

    instructions for cooking recipes

    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
    350
    +0.15
    0.5%
    390
    +0.13
    0.5%
    488
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    469
    +0.15
    0.03
    271
    +0.13
    0.02
    582
    +0.13
    0.02
    Negative Logits
    iven
    -0.95
     Grateful
    -0.87
    ilitary
    -0.85
    isphere
    -0.85
    dfx
    -0.85
    peria
    -0.83
    iami
    -0.80
     Sv
    -0.80
     Ost
    -0.80
     Bethesda
    -0.80
    POSITIVE LOGITS
    Cook
    1.14
     Bake
    0.92
    zee
    0.88
     enzymes
    0.87
     pH
    0.87
    Recipe
    0.86
    iency
    0.85
    icer
    0.85
    cook
    0.84
     Cook
    0.84
    Activations Density 0.210%

    No Known Activations