© 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. 36834
    Prev
    Next
    INDEX
    Explanations

    text related to legal cases or political statements

    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
    447
    +0.41
    2.3%
    481
    +0.13
    0.7%
    718
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.41
    0.37
    169
    +0.13
    0.19
    149
    +0.11
    0.09
    Negative Logits
    interstitial
    -0.55
     OG
    -0.52
    rx
    -0.50
     crap
    -0.49
    Posts
    -0.49
    200000
    -0.49
    ses
    -0.49
    Enlarge
    -0.49
     Guinea
    -0.48
    Appearances
    -0.48
    POSITIVE LOGITS
    've
    0.89
     intend
    0.85
     apologise
    0.79
     hope
    0.78
     propose
    0.77
     respectfully
    0.76
     conclude
    0.75
     sincerely
    0.74
     cannot
    0.74
     endeav
    0.73
    Activations Density 19.305%

    No Known Activations