© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8621
    Prev
    Next
    INDEX
    Explanations

    mentions of rebel groups or insurgency

    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
    447
    +0.16
    0.7%
    288
    +0.13
    0.6%
    154
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    154
    +0.16
    0.02
    288
    +0.13
    0.02
    523
    +0.12
    0.02
    Negative Logits
    ographies
    -0.81
    ocobo
    -0.77
    è¯
    -0.74
    uchin
    -0.73
    thora
    -0.72
    icrobial
    -0.69
    gow
    -0.67
    Safety
    -0.67
     Hilbert
    -0.66
     Robo
    -0.66
    POSITIVE LOGITS
     factions
    1.07
     rebels
    1.01
     faction
    0.95
     militias
    0.95
     milit
    0.94
     rebel
    0.93
     fighters
    0.92
     stronghold
    0.91
     strongh
    0.88
     army
    0.87
    Activations Density 0.024%

    No Known Activations