© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3222
    Prev
    Next
    INDEX
    Explanations

    phrases related to betting or wagering

    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    283
    +0.20
    0.6%
    288
    +0.18
    0.6%
    187
    +0.17
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.20
    0.09
    326
    +0.18
    0.07
    187
    +0.17
    0.06
    Negative Logits
    ĸļ
    -1.20
    VILLE
    -1.13
    pmwiki
    -1.07
     prosec
    -1.07
    AND
    -1.02
    ocumented
    -1.00
    issance
    -0.98
    士
    -0.97
     Flavoring
    -0.97
    mite
    -0.96
    POSITIVE LOGITS
    hesda
    1.69
    ting
    1.49
    tery
    1.38
     bets
    1.33
     bet
    1.23
    ters
    1.21
    rol
    1.17
    terson
    1.11
    terness
    1.11
    eful
    1.08
    Activations Density 1.359%

    No Known Activations