© 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 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. 11041
    Prev
    Next
    INDEX
    Explanations

    references to actions involving flipping or turning something over

    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
    288
    +0.13
    0.6%
    189
    +0.13
    0.6%
    195
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    189
    +0.13
    0.02
    28
    +0.13
    0.01
    569
    +0.11
    0.01
    Negative Logits
    lain
    -0.84
    Interstitial
    -0.78
    hart
    -0.76
    aph
    -0.72
    FORE
    -0.72
    Requires
    -0.70
    needs
    -0.68
    chell
    -0.68
     Annotations
    -0.67
    hips
    -0.67
    POSITIVE LOGITS
    olitics
    0.90
    switch
    0.87
     burgers
    0.84
     flipped
    0.83
     flo
    0.82
    tera
    0.80
    osition
    0.78
     flip
    0.78
    bill
    0.78
     pend
    0.77
    Activations Density 0.022%

    No Known Activations