© 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. 24017
    Prev
    Next
    INDEX
    Explanations

    quotes or speech within the text

    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
    107
    +0.13
    0.6%
    6
    +0.11
    0.5%
    627
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.13
    0.05
    452
    +0.11
    0.04
    6
    +0.11
    0.05
    Negative Logits
     parting
    -0.82
     periodic
    -0.80
     confir
    -0.77
     favor
    -0.77
     scheduled
    -0.76
     dispos
    -0.76
     adjud
    -0.76
     brid
    -0.74
     sway
    -0.73
     dispar
    -0.73
    POSITIVE LOGITS
    They
    1.53
    We
    1.48
    It
    1.48
    Especially
    1.47
    I
    1.46
    Because
    1.44
    Nobody
    1.44
    Everybody
    1.41
    But
    1.40
    There
    1.39
    Activations Density 0.088%

    No Known Activations