© 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. 40674
    Prev
    Next
    INDEX
    Explanations

    scientific and medical terminology related to body systems and functions, as well as implications of medical studies

    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
    +0.23
    0.9%
    407
    +0.11
    0.4%
    525
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.23
    0.23
    675
    +0.11
    0.18
    488
    +0.11
    0.18
    Negative Logits
    geries
    -1.13
    ariat
    -0.82
    gery
    -0.80
     bunny
    -0.77
    adra
    -0.76
     ears
    -0.74
     amaz
    -0.73
     bung
    -0.72
     Bung
    -0.71
    .):
    -0.71
    POSITIVE LOGITS
     Conversely
    1.13
     Similarly
    1.04
     Moreover
    0.97
    However
    0.96
     Likewise
    0.95
     Alternatively
    0.95
     Notably
    0.94
     Furthermore
    0.93
    Likewise
    0.92
    Therefore
    0.92
    Activations Density 11.719%

    No Known Activations