© 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. 1310
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals' names

    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
    659
    +0.14
    0.7%
    213
    +0.11
    0.5%
    418
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.03
    213
    +0.11
    0.02
    413
    +0.09
    0.01
    Negative Logits
    ties
    -0.78
    ï¸ı
    -0.73
    ãĤ¤ãĥĪ
    -0.72
    INGS
    -0.70
    manship
    -0.70
     spare
    -0.67
    */(
    -0.66
     actionGroup
    -0.64
    ividual
    -0.63
    ilater
    -0.63
    POSITIVE LOGITS
    abol
    1.35
    agram
    1.31
    abolic
    1.25
    ocese
    1.25
    agonal
    1.21
    ploma
    1.20
    plom
    1.19
    urnal
    1.14
    abetic
    1.12
    abetes
    1.12
    Activations Density 0.012%

    No Known Activations