© 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. 9053
    Prev
    Next
    INDEX
    Explanations

    details related to crime scenes and incidents

    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
    362
    +0.19
    0.9%
    393
    +0.15
    0.7%
    385
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.19
    0.11
    385
    +0.15
    0.07
    393
    +0.11
    0.07
    Negative Logits
    IRED
    -0.77
    loads
    -0.76
    omics
    -0.75
    ipedia
    -0.73
    osponsors
    -0.72
    HUD
    -0.71
    ogh
    -0.70
    govtrack
    -0.70
    landers
    -0.69
    nav
    -0.69
    POSITIVE LOGITS
     vicinity
    1.19
     same
    1.10
     incident
    1.03
     altercation
    1.03
     aftermath
    1.02
     doorway
    0.98
     roadway
    0.97
     intervening
    0.97
     driveway
    0.96
     hallway
    0.94
    Activations Density 0.325%

    No Known Activations