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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13967
    Prev
    Next
    INDEX
    Explanations

    people's names and locations

    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
    466
    +0.08
    0.5%
    715
    +0.08
    0.5%
    567
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    398
    +0.08
    0.08
    442
    +0.08
    0.07
    353
    +0.08
    0.07
    Negative Logits
    ailability
    -0.62
    ecause
    -0.56
     concess
    -0.55
    berra
    -0.52
    webkit
    -0.52
     colleges
    -0.50
    ELF
    -0.50
     substance
    -0.50
     citiz
    -0.49
     conflic
    -0.49
    POSITIVE LOGITS
    furt
    0.71
    adder
    0.69
    stad
    0.69
    wagen
    0.68
    velt
    0.66
    kamp
    0.60
    poll
    0.60
    forth
    0.58
    fleet
    0.57
    lund
    0.57
    Activations Density 9.754%

    No Known Activations