© 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. 1-RES-JB
    11. 20539
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific geographical location named Pensacola

    oai_token-act-pair · gpt-3.5-turbo

    references to the location Pensacola

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Gleaming
    -0.74
    ORGE
    -0.73
    Rush
    -0.68
    ADS
    -0.67
    IELD
    -0.65
    ãģĦ
    -0.65
    tra
    -0.62
    ppo
    -0.62
    tz
    -0.62
    LOAD
    -0.62
    POSITIVE LOGITS
     Pens
    1.35
    insula
    1.12
    manship
    0.97
    caps
    0.96
    uits
    0.94
    awan
    0.93
    iments
    0.91
    uit
    0.88
    ensical
    0.87
    itent
    0.87
    Activations Density 0.011%

    No Known Activations