© 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. 12-RES-JB
    11. 2322
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to locations

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    references to the state of being or existence of subjects

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    krit
    -0.79
    rates
    -0.72
    mination
    -0.70
    cern
    -0.69
    sers
    -0.67
    dayName
    -0.67
    Scroll
    -0.66
    brates
    -0.66
    asury
    -0.66
    berus
    -0.66
    POSITIVE LOGITS
     witnessing
    1.08
     wasting
    1.02
     screwed
    0.96
     missing
    0.96
     dealing
    0.93
     dreaming
    0.90
     doomed
    0.89
     risking
    0.87
     toast
    0.87
     overlooking
    0.85
    Activations Density 0.176%

    No Known Activations