© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 16742
    Prev
    Next
    INDEX
    Explanations

    the phrase "only one."

    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
    408
    +0.13
    0.6%
    609
    +0.12
    0.5%
    223
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    223
    +0.13
    0.04
    609
    +0.12
    0.04
    25
    +0.10
    0.03
    Negative Logits
    ooks
    -0.94
    its
    -0.93
    folk
    -0.85
    ortunately
    -0.82
    acements
    -0.80
    apons
    -0.76
    hips
    -0.75
    bows
    -0.74
    Downloadha
    -0.74
    ãĥ¼
    -0.74
    POSITIVE LOGITS
     hundred
    1.17
     thing
    1.07
     person
    1.06
     hour
    1.01
     instance
    0.99
     aspect
    0.95
     ounce
    0.94
     piece
    0.93
     thousand
    0.92
     month
    0.92
    Activations Density 0.075%

    No Known Activations