© 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. 11926
    Prev
    Next
    INDEX
    Explanations

    statistics and details related to sports matches and player performance

    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
    86
    +0.12
    0.6%
    492
    +0.10
    0.5%
    323
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.12
    0.05
    86
    +0.10
    0.05
    546
    +0.10
    0.05
    Negative Logits
    itarian
    -0.82
    onym
    -0.77
    ire
    -0.74
    izen
    -0.74
    iless
    -0.73
    insula
    -0.73
    reprene
    -0.70
    sylv
    -0.70
    iq
    -0.69
    chin
    -0.68
    POSITIVE LOGITS
     finishing
    1.08
     scoring
    1.06
     albeit
    0.99
     totaling
    0.99
     culminating
    0.99
     averaging
    0.98
     prompting
    0.96
     forcing
    0.94
     tying
    0.93
     allowing
    0.93
    Activations Density 0.213%

    No Known Activations