© 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 1536
    9. 8-RES_FS1536-JB
    11. 1045
    Prev
    Next
    INDEX
    Explanations

    confidence and certainty in 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_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    243
    +0.11
    0.5%
    28
    +0.10
    0.5%
    172
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.11
    0.12
    8
    +0.10
    0.10
    243
    +0.09
    0.10
    Negative Logits
    iless
    -0.71
    thood
    -0.70
    ories
    -0.69
    psey
    -0.66
    matically
    -0.63
    cially
    -0.63
    idas
    -0.62
    vati
    -0.60
    ilaterally
    -0.60
    inth
    -0.59
    POSITIVE LOGITS
     surprises
    0.70
     Rampage
    0.70
     admire
    0.67
     plenty
    0.66
     delight
    0.65
     delighted
    0.65
    âĶĢ
    0.65
     adore
    0.63
     grinning
    0.63
     displeasure
    0.62
    Activations Density 3.198%

    No Known Activations