© 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. 12288
    Prev
    Next
    INDEX
    Explanations

    words related to violence involving relationships and conflict

    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
    124
    +0.12
    0.5%
    687
    +0.11
    0.5%
    245
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    636
    +0.12
    0.03
    124
    +0.11
    0.04
    362
    +0.10
    0.04
    Negative Logits
    eret
    -0.80
    Wide
    -0.73
    taboola
    -0.70
    ometer
    -0.70
    oute
    -0.70
    akeru
    -0.68
    antine
    -0.67
    ĸļ
    -0.67
    eele
    -0.67
    soType
    -0.65
    POSITIVE LOGITS
     unborn
    0.98
     innocent
    0.97
     messenger
    0.93
     entire
    0.92
     whistle
    0.87
     intruder
    0.86
     unarmed
    0.86
     innoc
    0.85
     offending
    0.81
     hostages
    0.80
    Activations Density 0.178%

    No Known Activations