© 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 49152
    9. 8-RES_FS49152-JB
    11. 45756
    Prev
    Next
    INDEX
    Explanations

    references to statistical percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    676
    +0.10
    0.4%
    661
    +0.09
    0.4%
    718
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    661
    +0.10
    0.01
    676
    +0.09
    0.01
    412
    +0.09
    0.01
    Negative Logits
    æ©
    -0.79
    士
    -0.78
    IRT
    -0.74
    ebus
    -0.70
    çīĪ
    -0.69
    ITED
    -0.69
    itans
    -0.69
    sbm
    -0.68
    gotten
    -0.66
    bley
    -0.66
    POSITIVE LOGITS
     (%)
    0.81
     percentage
    0.79
     percentages
    0.76
    pointer
    0.76
    ttle
    0.71
     ceilings
    0.71
     accuracy
    0.71
     coefficient
    0.70
    point
    0.70
     degree
    0.68
    Activations Density 0.007%

    No Known Activations