© 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. 8645
    Prev
    Next
    INDEX
    Explanations

    criminal activities or incidents related to violence and robbery

    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
    369
    +0.10
    0.5%
    321
    +0.10
    0.5%
    178
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.10
    0.07
    546
    +0.10
    0.07
    765
    +0.10
    0.06
    Negative Logits
    ire
    -0.68
    ocus
    -0.64
     Ratings
    -0.64
    roads
    -0.61
    rastructure
    -0.60
     Consortium
    -0.59
    chieve
    -0.58
     Month
    -0.58
     Investment
    -0.58
    ocl
    -0.57
    POSITIVE LOGITS
     prompting
    1.09
     injuring
    0.94
     resulting
    0.94
     causing
    0.91
     intending
    0.88
     according
    0.87
     thereby
    0.86
    then
    0.86
     unaware
    0.83
     forcing
    0.83
    Activations Density 0.334%

    No Known Activations