© 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. 8665
    Prev
    Next
    INDEX
    Explanations

    mentions of opposing forces or conflicts

    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
    447
    +0.17
    0.8%
    703
    +0.13
    0.6%
    740
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    703
    +0.17
    0.03
    498
    +0.13
    0.03
    339
    +0.11
    0.03
    Negative Logits
    risome
    -0.77
    inarily
    -0.72
    idable
    -0.71
    tten
    -0.66
    ographically
    -0.65
    elcome
    -0.65
    etitive
    -0.64
    atern
    -0.63
    edient
    -0.63
    ably
    -0.62
    POSITIVE LOGITS
     guiActiveUnfocused
    0.68
     Skydragon
    0.67
     HW
    0.67
    ï¸ı
    0.66
     CoC
    0.66
     HRC
    0.61
     Squirrel
    0.59
    actionDate
    0.59
     deduction
    0.58
     CV
    0.58
    Activations Density 0.308%

    No Known Activations