© 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 EvalsExportsinterp-engineNEWAPI 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. 4186
    Prev
    Next
    INDEX
    Explanations

    violent acts and criminal behavior

    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
    474
    +0.14
    0.6%
    165
    +0.11
    0.5%
    742
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    570
    +0.14
    0.01
    282
    +0.11
    0.04
    165
    +0.11
    0.02
    Negative Logits
    ortium
    -0.64
     Accessed
    -0.64
     Interstellar
    -0.61
    Abstract
    -0.60
     redes
    -0.59
     Bulletin
    -0.58
     Progressive
    -0.57
     volcano
    -0.56
    mania
    -0.56
     sustainability
    -0.56
    POSITIVE LOGITS
     him
    1.48
    him
    1.23
     them
    1.23
    them
    1.05
     HIM
    1.02
     Him
    0.99
     THEM
    0.99
     hers
    0.86
     her
    0.83
     his
    0.82
    Activations Density 0.396%

    No Known Activations