© 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. 31293
    Prev
    Next
    INDEX
    Explanations

    names of locations, especially those related to specific events or conflict

    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
    167
    +0.08
    0.5%
    445
    +0.07
    0.4%
    649
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.08
    0.24
    442
    +0.07
    0.07
    326
    +0.07
    0.24
    Negative Logits
    packing
    -0.54
    argon
    -0.53
    obar
    -0.53
    herty
    -0.51
    ibl
    -0.50
    itted
    -0.50
    ophile
    -0.50
    ĸļ
    -0.48
    isco
    -0.48
    orb
    -0.47
    POSITIVE LOGITS
    rats
    0.60
    DAQ
    0.59
    wash
    0.57
    gent
    0.56
    otle
    0.54
     Garden
    0.54
    tin
    0.54
    stall
    0.52
    utenant
    0.52
     Tanz
    0.52
    Activations Density 10.404%

    No Known Activations