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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 53
    Prev
    Next
    INDEX
    Explanations

    references to time intervals and academic processes

    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
    480
    +0.45
    2.3%
    481
    +0.12
    0.6%
    457
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.45
    0.00
    266
    +0.12
    0.11
    557
    +0.10
    0.04
    Negative Logits
    !.
    -0.85
    `.
    -0.81
    *.
    -0.80
    %.
    -0.77
    '.
    -0.74
    +.
    -0.74
    .*
    -0.68
    .","
    -0.68
    $.
    -0.67
    .[
    -0.66
    POSITIVE LOGITS
    pires
    0.58
    apeake
    0.58
     involves
    0.57
     constitutes
    0.56
     varies
    0.56
    MpServer
    0.56
     depends
    0.54
     differed
    0.53
     outweigh
    0.52
     depended
    0.51
    Activations Density 1.671%

    No Known Activations