© 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. 7893
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific experiments and technology

    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
    476
    +0.10
    0.4%
    256
    +0.09
    0.4%
    590
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.10
    0.01
    326
    +0.09
    0.07
    678
    +0.09
    0.04
    Negative Logits
     Canaver
    -0.68
     indispensable
    -0.61
     Rohingya
    -0.61
    apego
    -0.61
     Encyclopedia
    -0.61
     Emir
    -0.60
     antidote
    -0.60
    escription
    -0.60
     unmist
    -0.57
    aeper
    -0.56
    POSITIVE LOGITS
     occasions
    0.91
     alike
    0.87
     increments
    0.84
    vironments
    0.83
    _.
    0.82
     contexts
    0.81
     situations
    0.79
    +.
    0.78
    $.
    0.77
     guiActiveUnfocused
    0.76
    Activations Density 0.745%

    No Known Activations