© 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. 31349
    Prev
    Next
    INDEX
    Explanations

    discussions related to financial concepts, such as debt, loans, budgets, and deficits

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.33
    1.8%
    393
    +0.15
    0.8%
    246
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    167
    +0.33
    0.01
    393
    +0.15
    0.37
    551
    +0.11
    0.14
    Negative Logits
    UTC
    -0.54
    UFF
    -0.50
    atory
    -0.49
    REDACTED
    -0.49
    shore
    -0.48
     Hels
    -0.47
    Ŀ
    -0.47
    noon
    -0.47
     Rory
    -0.47
    ciating
    -0.45
    POSITIVE LOGITS
    'll
    0.85
     MUST
    0.70
     SHALL
    0.70
    'd
    0.69
     surely
    0.69
     must
    0.65
     SHOULD
    0.65
     certainly
    0.64
    CHA
    0.61
     shouldn
    0.60
    Activations Density 19.508%

    No Known Activations