© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 2283
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparing or providing alternatives

    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
    221
    +0.10
    0.4%
    362
    +0.10
    0.4%
    669
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.10
    0.04
    210
    +0.10
    0.03
    669
    +0.10
    0.03
    Negative Logits
    fw
    -0.72
    ription
    -0.72
    206
    -0.61
    arta
    -0.60
    LED
    -0.60
    254
    -0.59
     stoked
    -0.59
    FTWARE
    -0.59
    618
    -0.59
    ivities
    -0.59
    POSITIVE LOGITS
     traditional
    0.95
     existing
    0.81
     conventional
    0.76
     stereotypical
    0.76
     ordinary
    0.75
     sorts
    0.73
    traditional
    0.72
     normal
    0.72
     usual
    0.69
     typical
    0.67
    Activations Density 0.138%

    No Known Activations