© 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. 16828
    Prev
    Next
    INDEX
    Explanations

    words related to criminal activities or violent 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
    288
    +0.15
    0.7%
    404
    +0.11
    0.5%
    231
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.01
    232
    +0.11
    0.01
    661
    +0.10
    0.01
    Negative Logits
    WAYS
    -0.73
    VERTISEMENT
    -0.66
     tighter
    -0.66
     tightening
    -0.66
     fueling
    -0.65
    Factor
    -0.64
    OPLE
    -0.64
     constraints
    -0.63
     centrif
    -0.63
     forth
    -0.62
    POSITIVE LOGITS
    oria
    1.34
    oire
    1.31
    orious
    1.30
    orian
    1.25
    ory
    1.21
    orius
    1.20
    ims
    1.15
    orians
    1.12
    oric
    1.08
    rol
    1.07
    Activations Density 0.020%

    No Known Activations