© 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. 45801
    Prev
    Next
    INDEX
    Explanations

    past tense and present participle forms of the verb "play."

    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
    761
    +0.12
    0.6%
    540
    +0.11
    0.5%
    70
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    761
    +0.12
    0.04
    540
    +0.11
    0.03
    212
    +0.09
    0.03
    Negative Logits
    İ
    -0.67
    brow
    -0.64
     Shipping
    -0.64
     Beir
    -0.63
    Purchase
    -0.60
    Ĭ±
    -0.59
    fty
    -0.59
    sav
    -0.59
    appro
    -0.58
    icon
    -0.58
    POSITIVE LOGITS
    wright
    0.91
     colleg
    0.87
    ername
    0.86
     alongside
    0.86
     against
    0.83
     fullback
    0.80
     played
    0.79
     football
    0.73
     poker
    0.71
    heet
    0.71
    Activations Density 0.035%

    No Known Activations