© 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 Local
    9. 6-RES_SCL-AJT
    11. 33085
    Prev
    Next
    INDEX
    Explanations

    references to specific amounts of money

    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
    +0.23
    1.0%
    762
    +0.12
    0.5%
    316
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    35
    +0.23
    0.07
    729
    +0.12
    0.07
    241
    +0.10
    0.07
    Negative Logits
    ãĤ¦ãĤ¹
    -0.76
    ICLE
    -0.76
     Emin
    -0.70
     cannabin
    -0.70
     Halls
    -0.69
    âĹ¼
    -0.69
     Oss
    -0.68
    ople
    -0.68
     Leth
    -0.66
     Stru
    -0.66
    POSITIVE LOGITS
     dollars
    0.96
     laundering
    0.95
     USD
    0.93
     apiece
    0.92
     ($
    0.92
     sterling
    0.92
     worth
    0.91
     annually
    0.86
     per
    0.86
    /$
    0.85
    Activations Density 5.431%

    No Known Activations