© 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. 2764
    Prev
    Next
    INDEX
    Explanations

    references to science fiction concepts and technological products

    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
    480
    +0.56
    3.0%
    266
    +0.13
    0.7%
    237
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.56
    0.02
    266
    +0.13
    0.07
    284
    +0.09
    0.05
    Negative Logits
    nesday
    -0.66
    ĵĺ
    -0.60
    leck
    -0.57
    itiveness
    -0.53
    bitious
    -0.52
    ruary
    -0.50
    illet
    -0.48
    icipated
    -0.48
    uesday
    -0.48
    enture
    -0.48
    POSITIVE LOGITS
    ibrary
    0.72
    oxide
    0.62
     Pos
    0.55
    otide
    0.54
     Sanct
    0.54
    ãĥĺãĥ©
    0.54
    ioxide
    0.53
     Species
    0.51
    ãĤ´
    0.49
    utable
    0.49
    Activations Density 0.690%

    No Known Activations