© 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. 17360
    Prev
    Next
    INDEX
    Explanations

    words related to hostility or conflict , especially in a political context

    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
    +0.12
    0.6%
    278
    +0.09
    0.4%
    247
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    329
    +0.12
    0.01
    278
    +0.09
    0.01
    247
    +0.09
    0.01
    Negative Logits
    ucket
    -0.95
    orah
    -0.81
    otide
    -0.75
    utters
    -0.75
    ainers
    -0.75
    illon
    -0.75
    annis
    -0.74
    frey
    -0.74
    amura
    -0.72
    tall
    -0.71
    POSITIVE LOGITS
     takeover
    1.02
     toward
    0.93
     hostile
    0.88
     towards
    0.87
     retaliation
    0.84
     reception
    0.81
     retribution
    0.79
     glare
    0.78
     atmosp
    0.77
     posture
    0.77
    Activations Density 0.033%

    No Known Activations