© 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. 31568
    Prev
    Next
    INDEX
    Explanations

    names and locations of various people and places

    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
    235
    +0.14
    0.6%
    274
    +0.11
    0.4%
    73
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.09
    701
    +0.11
    0.06
    190
    +0.10
    0.07
    Negative Logits
     Halls
    -0.72
    {"
    -0.72
     Saskatchewan
    -0.70
     dime
    -0.69
     Grayson
    -0.67
     Koz
    -0.64
     Dragons
    -0.63
    irements
    -0.63
     Thatcher
    -0.63
     Victoria
    -0.61
    POSITIVE LOGITS
    agus
    1.15
    wered
    1.10
    ream
    0.96
    ylum
    0.90
    aucas
    0.90
    ersion
    0.88
    ociated
    0.88
    roma
    0.85
    allah
    0.84
    ipal
    0.83
    Activations Density 5.981%

    No Known Activations