© 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. 13734
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical altercations and injuries

    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
    722
    +0.11
    0.5%
    714
    +0.10
    0.4%
    762
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    714
    +0.11
    0.04
    289
    +0.10
    0.01
    581
    +0.10
    0.03
    Negative Logits
    agonist
    -0.92
    assad
    -0.86
    imum
    -0.85
    ipolar
    -0.80
     scheduling
    -0.78
     IST
    -0.78
    onomous
    -0.78
     Promotion
    -0.77
    thood
    -0.77
    anta
    -0.77
    POSITIVE LOGITS
     charred
    1.42
     rotting
    1.35
     rubble
    1.28
     debris
    1.28
     stains
    1.24
     burnt
    1.21
     wreckage
    1.20
     littered
    1.14
     corro
    1.12
     carc
    1.11
    Activations Density 0.469%

    No Known Activations