© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9097
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific type of item that can be purchased or found in different locations

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    393
    +0.24
    0.8%
    484
    +0.21
    0.7%
    616
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.24
    0.08
    614
    +0.21
    0.06
    616
    +0.17
    0.06
    Negative Logits
    rex
    -1.09
    seless
    -1.00
    endas
    -1.00
    rea
    -0.97
    appings
    -0.94
    icz
    -0.88
    rez
    -0.88
    arium
    -0.87
    opsis
    -0.86
    lights
    -0.86
    POSITIVE LOGITS
    THING
    1.66
     conceivable
    1.40
    where
    1.32
    WHERE
    1.31
     imaginable
    1.30
    body
    1.28
    ONE
    1.18
     other
    1.15
     kind
    1.14
     else
    1.14
    Activations Density 0.707%

    No Known Activations