© 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 1536
    9. 8-RES_FS1536-JB
    11. 1098
    Prev
    Next
    INDEX
    Explanations

    religious texts or references

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    350
    +0.10
    0.5%
    239
    +0.10
    0.4%
    25
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    25
    +0.10
    0.06
    350
    +0.10
    0.07
    223
    +0.09
    0.07
    Negative Logits
     interns
    -0.83
    Bernie
    -0.77
     trends
    -0.76
    ulton
    -0.76
     Trend
    -0.76
     derail
    -0.75
     clips
    -0.73
    CTV
    -0.72
    leneck
    -0.72
     editorial
    -0.71
    POSITIVE LOGITS
     Almighty
    1.46
     scripture
    1.41
     divine
    1.40
     Apostle
    1.40
     Scripture
    1.36
     deity
    1.32
     Apostles
    1.31
     prophets
    1.31
     Blessed
    1.31
     Divine
    1.30
    Activations Density 2.966%

    No Known Activations