© 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. 16152
    Prev
    Next
    INDEX
    Explanations

    programming code snippets related to regular expressions, memory sanitation, and buffer overflow detection

    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
    158
    +0.12
    0.5%
    248
    +0.11
    0.5%
    747
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.04
    158
    +0.11
    0.04
    586
    +0.09
    0.03
    Negative Logits
     earthqu
    -0.68
     Schne
    -0.67
     Schwe
    -0.66
     Rap
    -0.66
     Tai
    -0.66
     Britann
    -0.66
     Buch
    -0.65
     reluct
    -0.65
     unden
    -0.64
     streng
    -0.64
    POSITIVE LOGITS
    _
    1.48
    ()
    1.36
    __
    1.15
    ())
    1.09
     ()
    1.07
    ();
    1.06
    _-_
    1.04
    ().
    1.03
    ():
    1.00
    ql
    1.00
    Activations Density 0.128%

    No Known Activations