© 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. 19465
    Prev
    Next
    INDEX
    Explanations

    references to criminal activities and police investigations

    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
    679
    +0.10
    0.5%
    373
    +0.10
    0.5%
    142
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    142
    +0.10
    0.04
    441
    +0.10
    0.03
    101
    +0.09
    0.04
    Negative Logits
    izont
    -0.85
    Translation
    -0.82
    ãĤ«
    -0.80
    milo
    -0.78
    Ranked
    -0.78
    çľ
    -0.77
    TABLE
    -0.76
    Newsletter
    -0.76
    Quantity
    -0.75
    2020
    -0.74
    POSITIVE LOGITS
     Sergeant
    1.00
     Sgt
    0.89
     troopers
    0.89
     investigators
    0.87
     detectives
    0.83
     Investigators
    0.83
     Officer
    0.82
     officers
    0.81
     Trooper
    0.81
     Fatal
    0.80
    Activations Density 0.117%

    No Known Activations