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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1451
    Prev
    Next
    INDEX
    Explanations

    steps or instructions in a procedure or guide

    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
    447
    +0.17
    0.6%
    739
    +0.16
    0.6%
    213
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.17
    0.08
    744
    +0.16
    0.07
    739
    +0.15
    0.04
    Negative Logits
    hips
    -0.91
    creen
    -0.88
    pless
    -0.88
    rums
    -0.88
    irtual
    -0.86
    ardless
    -0.85
    atform
    -0.84
    meet
    -0.84
    tight
    -0.83
    liberal
    -0.83
    POSITIVE LOGITS
     Advice
    1.07
    Recipe
    1.00
    Tips
    0.98
     Procedure
    0.97
     Explan
    0.96
     Recipe
    0.95
     Answer
    0.95
    Maker
    0.94
     Description
    0.91
     Recipes
    0.90
    Activations Density 1.368%

    No Known Activations