© 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 49152
    9. 8-RES_FS49152-JB
    11. 41565
    Prev
    Next
    INDEX
    Explanations

    references to sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    582
    +0.12
    0.5%
    608
    +0.12
    0.5%
    679
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    729
    +0.12
    0.01
    241
    +0.12
    0.01
    50
    +0.11
    0.01
    Negative Logits
    QB
    -0.64
     apostle
    -0.62
    esthetic
    -0.61
    Jr
    -0.61
    ¯¯
    -0.60
     Saud
    -0.60
    verages
    -0.59
    STON
    -0.59
    issance
    -0.59
    ries
    -0.57
    POSITIVE LOGITS
    opian
    1.15
    ierrez
    1.09
    creen
    0.95
    pace
    0.95
    ulkan
    0.94
    atis
    0.93
    nikov
    0.93
    kin
    0.92
    ourcing
    0.92
    hift
    0.91
    Activations Density 0.005%

    No Known Activations