© 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 Local
    9. 6-RES_SCL-AJT
    11. 36903
    Prev
    Next
    INDEX
    Explanations

    values or numbers in a structured format

    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
    266
    +0.24
    1.2%
    274
    +0.10
    0.5%
    294
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.24
    0.11
    6
    +0.10
    0.20
    107
    +0.09
    0.08
    Negative Logits
     nomine
    -0.73
    itialized
    -0.66
     oun
    -0.65
     concess
    -0.63
     unden
    -0.62
    uphem
    -0.62
     fundament
    -0.61
    nesday
    -0.60
     describ
    -0.60
     prominently
    -0.58
    POSITIVE LOGITS
    ":"
    0.76
     attRot
    0.66
     Deaths
    0.59
     APPLIC
    0.58
    ":{"
    0.57
    },"
    0.57
     78
    0.56
     Marketable
    0.56
     0
    0.54
    ":"/
    0.53
    Activations Density 15.754%

    No Known Activations