© 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. 19379
    Prev
    Next
    INDEX
    Explanations

    words related to integration or being integrated

    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
    656
    +0.11
    0.5%
    288
    +0.11
    0.5%
    679
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    656
    +0.11
    0.02
    332
    +0.11
    0.02
    101
    +0.11
    0.02
    Negative Logits
    thur
    -0.78
    rpm
    -0.73
    \\\\\\\\
    -0.66
    efer
    -0.66
    ym
    -0.66
    zzy
    -0.65
    ulz
    -0.62
    akia
    -0.62
    \\\\\\\\\\\\\\\\
    -0.60
    ord
    -0.59
    POSITIVE LOGITS
     into
    1.03
     INTO
    0.90
     seamlessly
    0.89
     Into
    0.86
    rity
    0.78
     integration
    0.77
     circuits
    0.75
    rehensive
    0.74
    into
    0.73
     integrates
    0.71
    Activations Density 0.026%

    No Known Activations