© 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. 7792
    Prev
    Next
    INDEX
    Explanations

    descriptions of visual details, specifically focusing on clothing and appearances

    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
    373
    +0.22
    1.0%
    218
    +0.10
    0.5%
    58
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.22
    0.07
    373
    +0.10
    -0.01
    6
    +0.10
    0.04
    Negative Logits
     someday
    -0.80
     honors
    -0.78
     legalizing
    -0.76
    ¶
    -0.74
     UCS
    -0.74
     ACS
    -0.73
     legalize
    -0.72
     honoring
    -0.71
     honored
    -0.70
    uga
    -0.70
    POSITIVE LOGITS
     neighbour
    0.99
     neighbours
    0.92
    Scotland
    0.92
    £
    0.89
    Liverpool
    0.88
     apologise
    0.87
     £
    0.85
    Labour
    0.84
    UK
    0.80
    Channel
    0.80
    Activations Density 0.177%

    No Known Activations