© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12852
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a very large or endless quantity

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to boundless quantities or limitless possibilities

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    bourg
    -0.84
    acus
    -0.82
    ective
    -0.77
    iquette
    -0.76
    ector
    -0.73
    imer
    -0.70
    Reviewed
    -0.70
    FACE
    -0.68
    achev
    -0.67
    ainment
    -0.66
    POSITIVE LOGITS
     possibilities
    1.07
     amounts
    1.06
     regress
    0.99
     supply
    0.97
     amount
    0.93
     quantities
    0.90
     Tsukuyomi
    0.89
     loop
    0.83
     loops
    0.82
     repetition
    0.82
    Activations Density 0.083%

    No Known Activations