© 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. 5119
    Prev
    Next
    INDEX
    Explanations

    locations and geographical areas

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

    references to specific geographical areas or regions

    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
    aldi
    -0.77
    gins
    -0.76
    ANCE
    -0.76
    arus
    -0.76
    bones
    -0.75
    enstein
    -0.72
    inn
    -0.72
    enment
    -0.71
    tails
    -0.70
    bone
    -0.68
    POSITIVE LOGITS
     bounded
    1.04
     surrounding
    0.96
     frequ
    0.89
     nearest
    0.87
     around
    0.87
     encomp
    0.83
     where
    0.82
     adjoining
    0.80
     inhabited
    0.80
     adjacent
    0.79
    Activations Density 0.102%

    No Known Activations