© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 13112
    Prev
    Next
    INDEX
    Explanations

    references to sports events and competitions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    679
    +0.11
    0.5%
    116
    +0.11
    0.5%
    57
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    116
    +0.11
    0.02
    146
    +0.11
    0.02
    538
    +0.10
    0.02
    Negative Logits
    nces
    -0.74
    flies
    -0.71
    wal
    -0.68
    cki
    -0.66
    itable
    -0.66
    igan
    -0.66
     Panda
    -0.64
    nery
    -0.63
    vier
    -0.63
    perse
    -0.61
    POSITIVE LOGITS
    alm
    0.87
    hetamine
    0.79
    ICS
    0.79
    ropolitan
    0.77
    ropri
    0.72
    henko
    0.71
    rodu
    0.70
    EG
    0.69
    ICO
    0.68
    rompt
    0.67
    Activations Density 0.162%

    No Known Activations