© 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. 1047
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and appreciation

    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
    165
    +0.11
    0.5%
    301
    +0.10
    0.5%
    381
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    424
    +0.11
    0.07
    259
    +0.10
    0.06
    165
    +0.10
    0.04
    Negative Logits
    rooms
    -0.75
    change
    -0.67
    ther
    -0.64
    chedel
    -0.63
    conserv
    -0.62
    improve
    -0.61
    scan
    -0.61
    女
    -0.60
    FO
    -0.60
    dq
    -0.60
    POSITIVE LOGITS
    giving
    1.31
     acknowled
    0.90
    FUL
    0.88
    ledged
    0.85
    ifully
    0.84
     heavens
    0.84
    fulness
    0.81
     Allaah
    0.79
    ESCO
    0.78
    fully
    0.77
    Activations Density 2.245%

    No Known Activations