© 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. 9598
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software development and programming, such as 'threading,' 'transaction,' 'model,' 'callback,' and 'configuration.'

    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
    +0.44
    2.2%
    326
    +0.12
    0.6%
    266
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.44
    -0.00
    739
    +0.12
    0.04
    655
    +0.12
    0.06
    Negative Logits
    Amid
    -0.72
     resurg
    -0.68
     Amid
    -0.67
    nered
    -0.66
    crime
    -0.62
     Rodham
    -0.61
    Dear
    -0.61
    polit
    -0.59
    cellence
    -0.59
    ablishment
    -0.58
    POSITIVE LOGITS
     optional
    0.97
     defaults
    0.92
     default
    0.89
     exceptions
    0.88
     overwrite
    0.84
     excludes
    0.82
     optionally
    0.82
    Example
    0.80
     easiest
    0.80
     Example
    0.78
    Activations Density 1.340%

    No Known Activations