© 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. 12290
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer systems or programming

    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
    +0.45
    2.4%
    447
    +0.16
    0.8%
    481
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.45
    0.10
    480
    +0.16
    0.02
    266
    +0.13
    0.08
    Negative Logits
     reluct
    -0.59
     millenn
    -0.56
     Canaver
    -0.54
     Hoover
    -0.53
     Singer
    -0.53
     resurg
    -0.53
     whistleblowers
    -0.52
     panicked
    -0.51
     Slim
    -0.50
     nostalg
    -0.50
    POSITIVE LOGITS
     ().
    0.75
    ().
    0.70
    /(
    0.69
     depending
    0.64
     unless
    0.64
    *.
    0.62
     (~
    0.61
    Points
    0.61
    esian
    0.60
     or
    0.60
    Activations Density 0.711%

    No Known Activations