© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 9535
    Prev
    Next
    INDEX
    Explanations

    terms related to sports teams and player transactions, including player agreements, deals, and negotiations, in addition to mentions of specific players and teams

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    554
    +0.11
    0.5%
    314
    +0.11
    0.5%
    26
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    26
    +0.11
    0.02
    316
    +0.11
    0.02
    659
    +0.10
    0.02
    Negative Logits
    pread
    -0.81
    ELF
    -0.66
     oven
    -0.64
     EntityItem
    -0.63
    OME
    -0.62
    omes
    -0.59
    steps
    -0.59
     Ways
    -0.59
    ship
    -0.58
    nesses
    -0.58
    POSITIVE LOGITS
    idation
    1.37
    idated
    1.23
    ueless
    1.17
    uable
    1.16
    ibr
    1.14
    idity
    1.10
    uations
    1.08
    encia
    1.08
    uation
    1.07
    idate
    1.05
    Activations Density 0.046%

    No Known Activations