© 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. 36867
    Prev
    Next
    INDEX
    Explanations

    keywords related to a specific location, potentially focusing on cities or countries

    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
    314
    +0.15
    0.6%
    288
    +0.15
    0.6%
    211
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.15
    -0.02
    649
    +0.15
    0.05
    343
    +0.13
    0.07
    Negative Logits
    uncture
    -0.95
    selves
    -0.83
    dfx
    -0.81
    aunder
    -0.74
    esthetic
    -0.71
     CLSID
    -0.70
    afort
    -0.70
     Spac
    -0.70
     Europa
    -0.70
    éĹĺ
    -0.69
    POSITIVE LOGITS
    querque
    1.52
    rows
    1.33
    rito
    1.31
    geoning
    1.28
    rowing
    1.23
    ger
    1.19
    row
    1.13
    leigh
    1.09
    geon
    1.07
    rill
    1.06
    Activations Density 5.839%

    No Known Activations