© 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. 8659
    Prev
    Next
    INDEX
    Explanations

    positions of authority and their actions or statements

    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
    480
    +0.32
    1.6%
    447
    +0.23
    1.1%
    481
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    371
    +0.32
    0.06
    506
    +0.23
    0.05
    104
    +0.15
    0.05
    Negative Logits
    fw
    -0.64
    ãģį
    -0.63
    ankind
    -0.60
    Compar
    -0.59
    ãģı
    -0.55
    Condition
    -0.55
    ãĥ¼ãĥ³
    -0.54
    Tokens
    -0.54
    Required
    -0.52
    Reason
    -0.52
    POSITIVE LOGITS
     Rahul
    0.79
     warns
    0.78
    Joined
    0.75
     Says
    0.74
     extraord
    0.73
     Gina
    0.71
     admits
    0.71
     announces
    0.71
     says
    0.70
     denies
    0.69
    Activations Density 0.217%

    No Known Activations