© 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. 22078
    Prev
    Next
    INDEX
    Explanations

    mentions of the political party "Fiana Fáil."

    oai_token-act-pair · gpt-4o-miniTriggered 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
    114
    +0.13
    0.6%
    372
    +0.12
    0.6%
    263
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.02
    406
    +0.12
    0.02
    343
    +0.09
    0.01
    Negative Logits
    neys
    -0.76
    wolves
    -0.67
    lasses
    -0.66
    ienced
    -0.64
    layer
    -0.63
    ======
    -0.63
    birds
    -0.62
    raved
    -0.61
    RFC
    -0.61
    ONSORED
    -0.60
    POSITIVE LOGITS
    eus
    1.36
    uthor
    1.30
    ples
    1.06
    isance
    1.06
    vel
    0.95
    ïve
    0.89
    issance
    0.87
    ñ
    0.87
    emon
    0.84
    wn
    0.84
    Activations Density 0.028%

    No Known Activations