© 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. 19354
    Prev
    Next
    INDEX
    Explanations

    references to soccer players and clubs

    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
    286
    +0.12
    0.6%
    493
    +0.10
    0.5%
    10
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    286
    +0.12
    0.06
    493
    +0.10
    0.05
    10
    +0.10
    0.04
    Negative Logits
    equality
    -0.73
    ĸļ
    -0.73
     centuries
    -0.71
     Poverty
    -0.70
     literacy
    -0.70
     inequalities
    -0.69
    average
    -0.69
     poorest
    -0.68
    Hum
    -0.68
     defeats
    -0.66
    POSITIVE LOGITS
     plans
    1.20
     rumored
    1.16
     negotiations
    1.14
     feasibility
    1.06
     pending
    1.02
     TBA
    1.01
     forthcoming
    1.00
     timetable
    1.00
     contingency
    0.98
     undisclosed
    0.96
    Activations Density 1.047%

    No Known Activations