© 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. 12136
    Prev
    Next
    INDEX
    Explanations

    opinions or views expressed in political op-eds

    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
    373
    +0.15
    0.7%
    111
    +0.10
    0.5%
    50
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.02
    537
    +0.10
    0.02
    641
    +0.10
    0.02
    Negative Logits
     Beautiful
    -0.65
     Illum
    -0.61
     Dign
    -0.60
     GOODMAN
    -0.59
     Arabian
    -0.58
     Kens
    -0.58
     Flavoring
    -0.57
     Pyth
    -0.57
     Awakens
    -0.57
     EntityItem
    -0.57
    POSITIVE LOGITS
    comment
    0.81
    ansion
    0.78
    reply
    0.75
    gres
    0.75
    Ops
    0.74
    opt
    0.72
    pos
    0.71
    etric
    0.71
    ops
    0.71
    doc
    0.71
    Activations Density 0.027%

    No Known Activations