© 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. 8070
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or efforts made by individuals or groups towards a specific goal or cause

    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
    15
    +0.10
    0.5%
    41
    +0.10
    0.4%
    298
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    636
    +0.10
    0.02
    298
    +0.10
    0.02
    324
    +0.09
    0.02
    Negative Logits
    ÃŁ
    -0.80
    appa
    -0.75
    CLA
    -0.73
    Developer
    -0.72
    larg
    -0.71
    SHIP
    -0.70
    DA
    -0.66
    Administ
    -0.66
     Laur
    -0.66
    Delete
    -0.65
    POSITIVE LOGITS
     overboard
    1.28
     tant
    1.09
     towel
    1.01
     grenades
    0.99
     grenade
    0.86
     punches
    0.86
     wrench
    0.79
     thrown
    0.76
     curve
    0.74
     contrace
    0.73
    Activations Density 0.086%

    No Known Activations