© 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. 35419
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names of individuals, specifically those related to sports

    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
    447
    +0.16
    0.7%
    52
    +0.12
    0.5%
    628
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    628
    +0.16
    0.06
    651
    +0.12
    0.09
    192
    +0.10
    0.05
    Negative Logits
    aeda
    -1.22
    aukee
    -0.95
    ickr
    -0.80
    iment
    -0.78
    encing
    -0.75
    idences
    -0.72
    insula
    -0.70
     instability
    -0.70
     equilibrium
    -0.69
     podium
    -0.68
    POSITIVE LOGITS
    friend
    1.44
     Scouts
    1.25
    cott
    1.23
    boy
    1.10
    nton
    1.09
     Scout
    1.09
    hood
    1.08
    stown
    1.07
    boys
    1.06
    friends
    1.06
    Activations Density 6.778%

    No Known Activations