© 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 EvalsExportsinterp-engineNEWAPI 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. 17101
    Prev
    Next
    INDEX
    Explanations

    action words related to conflict or controversy

    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
    373
    +0.21
    1.2%
    314
    +0.12
    0.7%
    418
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    750
    +0.21
    0.04
    373
    +0.12
    -0.03
    526
    +0.09
    0.00
    Negative Logits
    FORE
    -0.63
     Citation
    -0.57
     pending
    -0.54
     contiguous
    -0.53
     Liberation
    -0.50
     Login
    -0.49
     commem
    -0.48
     preferably
    -0.47
    raq
    -0.46
     noon
    -0.46
    POSITIVE LOGITS
    ealous
    0.65
    =-=-
    0.63
    ħĭ
    0.61
    andra
    0.57
    ãĥ³ãĤ¸
    0.54
    ÃįÃį
    0.54
    mbuds
    0.54
    ĭ
    0.54
    iscal
    0.53
    andre
    0.53
    Activations Density 0.327%

    No Known Activations