© 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. 12464
    Prev
    Next
    INDEX
    Explanations

    words related to political conflicts or geographic locations

    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
    496
    +0.14
    0.7%
    464
    +0.11
    0.5%
    373
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    464
    +0.14
    0.01
    326
    +0.11
    0.01
    726
    +0.11
    0.01
    Negative Logits
    ĸļ
    -0.77
    ļé
    -0.75
    ¬¼
    -0.75
    eston
    -0.73
    Ĥ¬
    -0.71
    acca
    -0.70
    onent
    -0.70
    romeda
    -0.68
    sylv
    -0.67
    ermott
    -0.66
    POSITIVE LOGITS
    lli
    1.25
    nces
    1.20
    ttes
    1.06
    lla
    1.02
    lessly
    0.91
    ly
    0.90
    zza
    0.90
    tta
    0.88
    nder
    0.87
    ndra
    0.86
    Activations Density 0.031%

    No Known Activations