© 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. 12081
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific location or event

    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
    740
    +0.13
    0.6%
    373
    +0.10
    0.5%
    730
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.13
    0.02
    373
    +0.10
    -0.01
    740
    +0.10
    0.01
    Negative Logits
    yip
    -0.76
    iazep
    -0.66
    ndra
    -0.65
    ufact
    -0.62
    ursday
    -0.61
    nesday
    -0.56
     unbeliev
    -0.56
     emphasis
    -0.55
    abwe
    -0.54
     compr
    -0.54
    POSITIVE LOGITS
    crew
    0.85
    INAL
    0.79
    IED
    0.75
     Janeiro
    0.73
    oreal
    0.69
    othy
    0.69
    pora
    0.68
    Ķ
    0.67
    pine
    0.64
    ption
    0.64
    Activations Density 0.037%

    No Known Activations