© 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. 11-RES-JB
    11. 2291
    Prev
    Next
    INDEX
    Explanations

    dates and historical events

    oai_token-act-pair · gpt-3.5-turbo

    historical events and figures, particularly related to kings and significant dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lawy
    -0.68
    ngth
    -0.67
     lobb
    -0.67
     Cosponsors
    -0.66
    wcs
    -0.65
     VIDEOS
    -0.64
    Merit
    -0.64
    berman
    -0.61
    EStreamFrame
    -0.60
    ullivan
    -0.59
    POSITIVE LOGITS
     1300
    1.38
     1050
    1.37
     1700
    1.35
     1400
    1.35
     1600
    1.34
     1440
    1.33
     1840
    1.32
     1500
    1.31
     1800
    1.31
     1100
    1.31
    Activations Density 0.167%

    No Known Activations