© 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. 17512
    Prev
    Next
    INDEX
    Explanations

    negative or controversial terms related to politics or events

    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
    362
    +0.16
    0.7%
    145
    +0.11
    0.5%
    572
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.16
    0.06
    408
    +0.11
    0.06
    725
    +0.11
    0.04
    Negative Logits
    osponsors
    -0.89
    utics
    -0.87
    orthy
    -0.86
    yers
    -0.83
    orneys
    -0.81
    irms
    -0.81
    omever
    -0.77
    terness
    -0.77
    thia
    -0.77
    autions
    -0.76
    POSITIVE LOGITS
     triangle
    0.83
     trio
    0.79
     duo
    0.79
     pyramid
    0.75
     annual
    0.74
     Golden
    0.73
     Millennium
    0.73
     acronym
    0.73
     infamous
    0.73
     notion
    0.72
    Activations Density 0.211%

    No Known Activations