© 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. 13941
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms related to medical research and publication

    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
    316
    +0.13
    0.6%
    659
    +0.11
    0.5%
    745
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.13
    0.50
    447
    +0.11
    0.52
    64
    +0.11
    -0.20
    Negative Logits
     franchise
    -0.75
    oaded
    -0.73
     vanity
    -0.72
     Rivals
    -0.71
    BuyableInstoreAndOnline
    -0.70
    swing
    -0.69
    terday
    -0.68
     Borders
    -0.68
     Armageddon
    -0.68
     Rebirth
    -0.67
    POSITIVE LOGITS
     et
    1.14
    witz
    1.08
    mberg
    1.08
    gaard
    1.04
    auer
    0.99
    enstein
    0.98
    beck
    0.97
    hu
    0.95
    lett
    0.93
    acci
    0.92
    Activations Density 10.702%

    No Known Activations