© 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. 12311
    Prev
    Next
    INDEX
    Explanations

    terms related to conflict or opposition, including descriptions of war crimes and political tensions

    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
    545
    +0.12
    0.5%
    572
    +0.11
    0.5%
    561
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    587
    +0.12
    0.03
    545
    +0.11
    0.03
    561
    +0.11
    0.03
    Negative Logits
    Introduced
    -0.78
     nod
    -0.78
    ilk
    -0.70
    nce
    -0.69
     answer
    -0.66
    eus
    -0.64
    ghan
    -0.64
     thereof
    -0.63
    bie
    -0.63
    iments
    -0.62
    POSITIVE LOGITS
     sorts
    1.22
     theirs
    0.87
     attrition
    0.82
     Roses
    0.75
    course
    0.73
     hers
    0.73
    catch
    0.72
    ãĥĦ
    0.72
     ours
    0.71
     yours
    0.71
    Activations Density 0.090%

    No Known Activations