© 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. 5704
    Prev
    Next
    INDEX
    Explanations

    words related to political and government scandals and controversies, particularly related to military institutions

    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
    314
    +0.11
    0.5%
    102
    +0.11
    0.5%
    67
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.11
    0.03
    725
    +0.11
    0.03
    220
    +0.10
    0.03
    Negative Logits
    bilt
    -0.67
     Grave
    -0.64
     Nadu
    -0.64
     Enix
    -0.64
     Pharaoh
    -0.61
     Spartan
    -0.61
     Canaveral
    -0.60
     XY
    -0.60
     por
    -0.59
     Gent
    -0.58
    POSITIVE LOGITS
    ibli
    1.24
    raid
    1.19
    ibliography
    1.17
    rows
    1.16
    odies
    1.12
    ambo
    1.12
    idd
    1.11
    antam
    1.11
    itter
    1.11
    abbling
    1.11
    Activations Density 0.028%

    No Known Activations