© 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. 24447
    Prev
    Next
    INDEX
    Explanations

    actions related to changes and management processes

    oai_token-act-pair · gpt-4o-miniTriggered 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
    665
    +0.12
    0.6%
    41
    +0.11
    0.5%
    766
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.12
    0.08
    611
    +0.11
    0.06
    405
    +0.10
    0.06
    Negative Logits
     Thou
    -0.65
    bians
    -0.61
    zbollah
    -0.59
    rought
    -0.58
    scar
    -0.56
    shall
    -0.56
    onna
    -0.56
    Jews
    -0.55
    asketball
    -0.55
    industrial
    -0.54
    POSITIVE LOGITS
     them
    0.98
    uate
    0.97
     yourself
    0.89
     these
    0.84
     oneself
    0.84
     ourselves
    0.83
     your
    0.83
    ively
    0.82
     accordingly
    0.79
     it
    0.79
    Activations Density 0.375%

    No Known Activations