© 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. 8708
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparison or contrast

    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
    608
    +0.12
    0.6%
    393
    +0.09
    0.4%
    332
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    409
    +0.12
    0.03
    557
    +0.09
    0.03
    692
    +0.09
    0.03
    Negative Logits
     agre
    -0.68
    yll
    -0.65
    ular
    -0.60
    Interstitial
    -0.59
    ians
    -0.59
    unicip
    -0.58
    heit
    -0.57
    usage
    -0.57
     mas
    -0.56
    formance
    -0.55
    POSITIVE LOGITS
     thirds
    0.68
    ses
    0.63
    oused
    0.63
     finalists
    0.61
     Cups
    0.61
     theirs
    0.60
     Colo
    0.59
    eely
    0.59
    legged
    0.58
    milo
    0.58
    Activations Density 0.056%

    No Known Activations