© 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. 8121
    Prev
    Next
    INDEX
    Explanations

    physical attributes or features of objects

    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
    249
    +0.12
    0.6%
    218
    +0.11
    0.5%
    649
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.12
    0.04
    500
    +0.11
    0.04
    99
    +0.10
    0.03
    Negative Logits
    PDATE
    -0.75
    Bir
    -0.71
    BAT
    -0.69
    ãĤ©
    -0.67
    ologne
    -0.67
    BuyableInstoreAndOnline
    -0.66
    ixtures
    -0.66
    allo
    -0.66
    GGGGGGGG
    -0.66
    CAST
    -0.65
    POSITIVE LOGITS
     of
    0.95
     thereof
    0.91
     corner
    0.87
     ridge
    0.80
     slopes
    0.76
     slope
    0.76
     lobe
    0.75
     portion
    0.72
     protr
    0.71
     corners
    0.71
    Activations Density 0.198%

    No Known Activations