© 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. 10101
    Prev
    Next
    INDEX
    Explanations

    references to patents and trademark applications in a textual context

    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
    288
    +0.15
    0.7%
    524
    +0.13
    0.6%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    524
    +0.15
    0.02
    288
    +0.13
    0.02
    137
    +0.10
    0.01
    Negative Logits
     Lans
    -0.71
     Revel
    -0.70
     Isles
    -0.69
    ħĭ
    -0.65
    gaard
    -0.64
     Atmosp
    -0.64
    ashington
    -0.63
     Afric
    -0.63
     Staten
    -0.62
    esta
    -0.62
    POSITIVE LOGITS
     infringement
    1.07
     filings
    0.82
    enced
    0.82
     portfolio
    0.80
    onomy
    0.79
     examiner
    0.79
     granted
    0.79
    iously
    0.78
     expires
    0.77
    ability
    0.77
    Activations Density 0.021%

    No Known Activations