© 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. 31423
    Prev
    Next
    INDEX
    Explanations

    phrases discussing sports strategies or game analysis with a focus on specific players or tactics

    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
    +0.15
    0.8%
    393
    +0.13
    0.6%
    267
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.15
    0.14
    542
    +0.13
    0.11
    606
    +0.11
    0.12
    Negative Logits
    ãĤ¹ãĥĪ
    -0.72
    Ń·
    -0.67
    ãĥı
    -0.64
    »Ĵ
    -0.63
    esm
    -0.63
    Ħ
    -0.62
    ©¶æ¥µ
    -0.62
    quarters
    -0.61
    ãĥ©ãĥ³
    -0.61
    omo
    -0.60
    POSITIVE LOGITS
     trope
    0.82
     week
    0.77
     happening
    0.77
     happens
    0.74
     discrepancy
    0.73
     guy
    0.72
     arrangement
    0.71
     happen
    0.71
     madness
    0.70
     latest
    0.68
    Activations Density 6.065%

    No Known Activations