© 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. 1891
    Prev
    Next
    INDEX
    Explanations

    references to leadership positions in sports teams

    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
    377
    +0.17
    0.6%
    167
    +0.13
    0.4%
    386
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    377
    +0.17
    0.08
    759
    +0.13
    0.06
    182
    +0.12
    0.06
    Negative Logits
    PsyNetMessage
    -1.11
    terday
    -0.94
     Suc
    -0.92
     mell
    -0.86
    Constructed
    -0.85
     recip
    -0.83
     Strat
    -0.79
    eros
    -0.79
     chloride
    -0.79
     Typh
    -0.78
    POSITIVE LOGITS
    liner
    1.66
    canon
    1.66
    liners
    1.57
    quarter
    1.54
    butt
    1.50
    lining
    1.50
    phones
    1.49
    gear
    1.46
    dress
    1.41
    stock
    1.37
    Activations Density 1.526%

    No Known Activations