© 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. 12427
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical tasks involving crafting or repairing items

    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
    430
    +0.10
    0.5%
    17
    +0.10
    0.5%
    593
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    344
    +0.10
    0.04
    223
    +0.10
    0.03
    573
    +0.10
    0.02
    Negative Logits
    ndra
    -0.72
    ntil
    -0.71
    ħĭ
    -0.70
    llor
    -0.68
    Ü
    -0.68
    ativity
    -0.68
     Aware
    -0.65
    bably
    -0.63
    awaru
    -0.63
    cknow
    -0.62
    POSITIVE LOGITS
     precedence
    0.98
     toll
    0.80
     slack
    0.74
     chunk
    0.72
     cues
    0.72
    ovsky
    0.71
     electrons
    0.70
     milliseconds
    0.69
     chunks
    0.68
     nutrients
    0.67
    Activations Density 0.142%

    No Known Activations