© 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. 25706
    Prev
    Next
    INDEX
    Explanations

    specific symbols or characters, particularly currency symbols and special characters

    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
    160
    +0.11
    0.5%
    466
    +0.10
    0.5%
    311
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    311
    +0.11
    0.00
    176
    +0.10
    0.00
    166
    +0.10
    0.00
    Negative Logits
    ilitating
    -0.72
     wip
    -0.69
     livest
    -0.68
    itaire
    -0.67
    ktop
    -0.66
    kered
    -0.66
     mainline
    -0.65
    terness
    -0.62
    ecause
    -0.62
    ilitation
    -0.62
    POSITIVE LOGITS
    ĺ
    0.90
    Ĵ
    0.89
    ģ
    0.88
    itude
    0.86
    ãĥ³
    0.84
    ĭ
    0.83
    arters
    0.78
    ments
    0.77
    į
    0.76
    Ģ
    0.76
    Activations Density 0.004%

    No Known Activations