Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 4322
    Prev
    Next
    INDEX
    Explanations

    action-packed dynamics in sports or physical contests

    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
    •Layer 6 UMAP region: Mostly-local line at bottom - local

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    87
    +0.32
    3.3%
    64
    +0.22
    2.2%
    447
    +0.09
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.32
    0.21
    447
    +0.22
    0.22
    87
    +0.09
    -0.03
    Negative Logits
     rul
    -0.29
    ItemThumbnailImage
    -0.28
    )=(
    -0.27
     lawy
    -0.27
    ©¶æ
    -0.26
    etheless
    -0.26
    ossier
    -0.25
     Colossus
    -0.25
     Colo
    -0.24
     constitu
    -0.23
    POSITIVE LOGITS
     guiActiveUn
    0.28
    own
    0.27
    ively
    0.27
    uper
    0.26
    itial
    0.26
    én
    0.25
    weed
    0.25
    ibly
    0.25
    rock
    0.24
    imum
    0.24
    Activations Density 3.467%

    No Known Activations