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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 36658
    Prev
    Next
    INDEX
    Explanations

    locations or organizations related to metropolitan areas

    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
    288
    +0.14
    0.6%
    447
    +0.13
    0.6%
    707
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.20
    752
    +0.13
    0.10
    219
    +0.10
    0.06
    Negative Logits
    kick
    -0.81
    fty
    -0.78
    enes
    -0.77
    edin
    -0.73
    verted
    -0.73
    err
    -0.73
    ife
    -0.72
    vous
    -0.71
    pport
    -0.71
    girls
    -0.70
    POSITIVE LOGITS
    ropolitan
    0.99
     Statistical
    0.98
     Metropolitan
    0.88
     Borough
    0.82
     Region
    0.79
     Institution
    0.77
     Networks
    0.75
     Regional
    0.74
    olitan
    0.72
     Transportation
    0.72
    Activations Density 6.185%

    No Known Activations