© 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. 18647
    Prev
    Next
    INDEX
    Explanations

    information related to statistical data, research findings, and analysis in various fields such as healthcare, politics, and economics

    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
    172
    +0.12
    0.5%
    715
    +0.10
    0.5%
    294
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    172
    +0.12
    0.03
    294
    +0.10
    0.03
    262
    +0.10
    0.03
    Negative Logits
    inated
    -0.81
    illet
    -0.78
    him
    -0.77
    iotic
    -0.76
    iggurat
    -0.75
    ahime
    -0.75
    hack
    -0.74
    imag
    -0.74
    onomy
    -0.72
    ells
    -0.72
    POSITIVE LOGITS
     maintaining
    1.07
     retaining
    1.02
     others
    0.95
     simultaneously
    0.90
     preserving
    0.90
     keeping
    0.86
     sparing
    0.84
     permitting
    0.84
     acknowledging
    0.82
     ignoring
    0.81
    Activations Density 0.040%

    No Known Activations