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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4039
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to experimental findings and data analysis in a research context

    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
    +0.15
    0.6%
    67
    +0.13
    0.5%
    718
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    239
    +0.15
    0.08
    25
    +0.13
    0.06
    314
    +0.12
    -0.05
    Negative Logits
    iets
    -0.88
    onite
    -0.82
    pire
    -0.82
    piring
    -0.78
    alias
    -0.77
    inventoryQuantity
    -0.75
     supernatural
    -0.75
    conservancy
    -0.74
    ictional
    -0.74
    antic
    -0.74
    POSITIVE LOGITS
     ).
    1.13
     .)
    1.02
     ),
    1.00
     appendix
    0.99
     largeDownload
    0.99
     Brief
    0.97
     summar
    0.94
     Fig
    0.93
     graphs
    0.93
     Appendix
    0.92
    Activations Density 7.349%

    No Known Activations