© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 37228
    Prev
    Next
    INDEX
    Explanations

    mentions of Uganda and Rwanda

    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
    481
    +0.12
    0.6%
    311
    +0.12
    0.5%
    117
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    311
    +0.12
    0.00
    343
    +0.12
    0.01
    67
    +0.12
    0.01
    Negative Logits
    alty
    -0.83
    ccording
    -0.79
    */(
    -0.78
    ãĤ´ãĥ³
    -0.78
    BOOK
    -0.73
    âĸ¬
    -0.73
    ĪĴ
    -0.72
    bender
    -0.70
    perature
    -0.69
    uters
    -0.68
    POSITIVE LOGITS
    andan
    1.45
    arte
    0.92
    istani
    0.82
    rican
    0.82
     Ug
    0.81
    rica
    0.79
     Haram
    0.76
    gang
    0.72
    acity
    0.72
     Roose
    0.72
    Activations Density 0.007%

    No Known Activations