© 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. 16077
    Prev
    Next
    INDEX
    Explanations

    references to waves, often metaphorical or symbolic in nature

    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
    481
    +0.11
    0.5%
    393
    +0.11
    0.5%
    566
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    748
    +0.11
    0.02
    362
    +0.11
    0.03
    561
    +0.11
    0.03
    Negative Logits
    saf
    -0.73
    æ³
    -0.73
    ree
    -0.72
    vale
    -0.72
    aves
    -0.71
    jad
    -0.70
    most
    -0.70
    mate
    -0.68
    mates
    -0.68
    minus
    -0.67
    POSITIVE LOGITS
     negativity
    0.96
     publicity
    0.91
     arrivals
    0.85
     homegrown
    0.85
     discontent
    0.85
     misinformation
    0.84
     incoming
    0.82
     disruptive
    0.79
     controversy
    0.78
     criticism
    0.78
    Activations Density 0.113%

    No Known Activations