© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 10594
    Prev
    Next
    INDEX
    Explanations

    famous names and locations, possibly related to historical or public figures

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names and places, particularly those associated with historical or cultural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vana
    -1.00
    reon
    -0.96
    ngth
    -0.91
    lez
    -0.80
    uana
    -0.80
    xual
    -0.78
    rera
    -0.76
    detail
    -0.76
    vg
    -0.75
    ionics
    -0.75
    POSITIVE LOGITS
     Palace
    0.84
     Institution
    0.79
     Sachs
    0.73
     Strategies
    0.69
    bury
    0.68
     Island
    0.68
     County
    0.67
     Heights
    0.67
     Square
    0.67
     Interactive
    0.67
    Activations Density 0.184%

    No Known Activations