© 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 12288
    9. 8-RES_FS12288-JB
    11. 10558
    Prev
    Next
    INDEX
    Explanations

    sports-related information, such as player names, positions, accolades, and career details

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    373
    +0.20
    0.9%
    202
    +0.10
    0.4%
    278
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    278
    +0.20
    0.04
    241
    +0.10
    0.04
    116
    +0.09
    0.03
    Negative Logits
     Shant
    -0.71
     vigil
    -0.70
     ageing
    -0.67
     hem
    -0.66
    itars
    -0.63
     needles
    -0.63
     umb
    -0.63
     Canaver
    -0.63
     crem
    -0.62
     extant
    -0.61
    POSITIVE LOGITS
     Rookie
    1.14
    League
    1.08
     Playoff
    1.05
     Championship
    1.05
     Playoffs
    1.04
     Finals
    1.03
     postseason
    1.03
     playoff
    0.98
     playoffs
    0.94
    ournament
    0.89
    Activations Density 0.225%

    No Known Activations