© 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. 12289
    Prev
    Next
    INDEX
    Explanations

    phrases describing specific events or situations

    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
    26
    +0.12
    0.6%
    582
    +0.12
    0.5%
    603
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    582
    +0.12
    0.06
    26
    +0.12
    0.07
    30
    +0.10
    0.05
    Negative Logits
    ding
    -0.71
    SPONSORED
    -0.70
    agin
    -0.70
    kaya
    -0.67
    whatever
    -0.66
    zzi
    -0.65
    aking
    -0.64
    åĤ
    -0.63
    udder
    -0.63
    \\\\\\\\
    -0.63
    POSITIVE LOGITS
    soever
    1.23
     asked
    1.10
     confronted
    1.06
     pressed
    1.00
     faced
    0.95
     contacted
    0.87
    ce
    0.86
     questioned
    0.85
     viewed
    0.81
     approached
    0.75
    Activations Density 0.084%

    No Known Activations