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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 11223
    Prev
    Next
    INDEX
    Explanations

    descriptions of customization options and upgrades in a digital context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    447
    +0.30
    1.6%
    481
    +0.22
    1.2%
    87
    +0.19
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.30
    0.12
    542
    +0.22
    0.07
    575
    +0.19
    0.09
    Negative Logits
    ĪĴ
    -0.61
    ?).
    -0.58
    catentry
    -0.52
    )."
    -0.52
    milo
    -0.50
    ).[
    -0.49
    cffffcc
    -0.49
    )).
    -0.48
     istg
    -0.48
    stant
    -0.47
    POSITIVE LOGITS
     besides
    0.62
     nowadays
    0.61
     thanks
    0.59
     regarding
    0.59
     involving
    0.56
     here
    0.55
     because
    0.55
    !:
    0.54
    .
    0.54
     depending
    0.54
    Activations Density 1.259%

    No Known Activations