© 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. 18715
    Prev
    Next
    INDEX
    Explanations

    locations where criminal incidents have occurred

    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
    640
    +0.15
    0.7%
    123
    +0.12
    0.6%
    362
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    123
    +0.15
    0.07
    121
    +0.12
    0.06
    66
    +0.11
    0.06
    Negative Logits
     inval
    -0.82
    issance
    -0.70
    âĿ
    -0.68
     thous
    -0.67
     physicists
    -0.67
    ibur
    -0.66
    CLASSIFIED
    -0.66
     engineers
    -0.66
    stall
    -0.64
     nurt
    -0.64
    POSITIVE LOGITS
     retaliation
    1.10
     conjunction
    1.09
     lieu
    1.08
     southwestern
    1.02
     accordance
    1.00
     southeastern
    0.97
     relation
    0.96
     downtown
    0.94
     northwestern
    0.94
     southwest
    0.91
    Activations Density 0.204%

    No Known Activations