© 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. 7784
    Prev
    Next
    INDEX
    Explanations

    names or titles related to law enforcement and crime investigation

    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
    23
    +0.15
    0.7%
    450
    +0.12
    0.5%
    288
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.15
    0.02
    450
    +0.12
    0.01
    232
    +0.09
    0.01
    Negative Logits
     microscope
    -0.68
    âĸ¬
    -0.64
    ======
    -0.63
     loopholes
    -0.62
    heads
    -0.61
     Presidency
    -0.61
     Sheen
    -0.60
    ptions
    -0.60
     microsc
    -0.60
     Leap
    -0.59
    POSITIVE LOGITS
    iatrics
    1.29
    igree
    1.27
    agog
    1.25
    iatric
    1.24
    aling
    1.09
    iments
    1.02
    iment
    1.01
    erson
    1.00
    antic
    0.98
    asus
    0.97
    Activations Density 0.023%

    No Known Activations