© 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. 24179
    Prev
    Next
    INDEX
    Explanations

    statements of opinion or assertion related to individuals and events

    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
    496
    +0.17
    0.8%
    314
    +0.12
    0.5%
    697
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    496
    +0.17
    0.07
    333
    +0.12
    0.06
    501
    +0.10
    0.06
    Negative Logits
     favour
    -0.82
     favor
    -0.82
     reflex
    -0.80
     clitor
    -0.77
     morph
    -0.74
     grazing
    -0.74
     scram
    -0.72
     targeted
    -0.71
     purported
    -0.71
     territorial
    -0.71
    POSITIVE LOGITS
    ï¸ı
    1.20
    Because
    1.02
    Otherwise
    1.00
    there
    0.99
    Therefore
    0.96
    It
    0.95
    They
    0.94
    Likewise
    0.92
    Secondly
    0.91
    Companies
    0.91
    Activations Density 0.118%

    No Known Activations