© 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. 19580
    Prev
    Next
    INDEX
    Explanations

    information related to actions or processes that involve significant changes or challenges

    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
    +0.11
    0.5%
    745
    +0.10
    0.4%
    225
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.11
    0.07
    288
    +0.10
    0.07
    575
    +0.10
    0.06
    Negative Logits
     cultured
    -0.73
     dearly
    -0.72
     extensively
    -0.67
    versely
    -0.66
     Tycoon
    -0.65
     Skies
    -0.65
     brightly
    -0.64
     strongest
    -0.63
     versatile
    -0.62
     Historically
    -0.62
    POSITIVE LOGITS
    zzle
    0.95
    uation
    0.85
     thereof
    0.82
    pletion
    0.79
    cation
    0.78
    ãĥīãĥ©
    0.74
    vation
    0.74
     thereafter
    0.73
    assian
    0.73
     completion
    0.72
    Activations Density 0.393%

    No Known Activations