© 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 24576
    9. 8-RES_FS24576-JB
    11. 19472
    Prev
    Next
    INDEX
    Explanations

    dates and locations related to historical events

    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
    666
    +0.11
    0.5%
    478
    +0.09
    0.4%
    184
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    375
    +0.11
    0.02
    666
    +0.09
    0.04
    260
    +0.08
    0.04
    Negative Logits
    ":"/
    -0.70
     Helpful
    -0.69
    ror
    -0.69
    ajor
    -0.66
     Certain
    -0.65
    ogenous
    -0.65
     notification
    -0.64
    notations
    -0.64
     Relationship
    -0.64
    ":""},{"
    -0.64
    POSITIVE LOGITS
     culminating
    0.94
     effortlessly
    0.94
     relentlessly
    0.90
     culminated
    0.87
     tirelessly
    0.85
    successfully
    0.83
     meticulously
    0.83
     merciless
    0.79
     dodging
    0.79
     toured
    0.78
    Activations Density 0.742%

    No Known Activations