© 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. 12192
    Prev
    Next
    INDEX
    Explanations

    negatively connotated terms or contexts

    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
    +0.16
    0.7%
    152
    +0.15
    0.7%
    157
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.16
    0.06
    314
    +0.15
    0.01
    639
    +0.12
    0.04
    Negative Logits
     Nicarag
    -0.74
     Manson
    -0.67
    ciating
    -0.67
     Revis
    -0.66
     Flores
    -0.63
     sodium
    -0.61
     dispatch
    -0.60
    selage
    -0.60
     extrem
    -0.60
     Bosnia
    -0.60
    POSITIVE LOGITS
    share
    1.08
    rate
    1.05
    out
    1.01
    through
    0.99
    along
    0.99
    away
    0.99
    cation
    0.99
    atten
    0.98
    outs
    0.98
    cycle
    0.96
    Activations Density 0.057%

    No Known Activations