© 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. 31122
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names

    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
    +0.17
    0.9%
    414
    +0.11
    0.6%
    538
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.17
    0.24
    709
    +0.11
    0.13
    414
    +0.10
    0.06
    Negative Logits
    akening
    -0.68
    ourt
    -0.66
    keye
    -0.59
    reek
    -0.59
     tremend
    -0.58
    hovah
    -0.57
    eny
    -0.57
    riv
    -0.57
    rium
    -0.56
    quant
    -0.54
    POSITIVE LOGITS
    inder
    0.92
    åĤ
    0.85
    gaard
    0.76
     Singh
    0.72
    jee
    0.70
    ance
    0.69
    holm
    0.65
    stall
    0.65
    gart
    0.64
    Deal
    0.63
    Activations Density 9.858%

    No Known Activations