© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 13359
    Prev
    Next
    INDEX
    Explanations

    locations and political figures related to the state of Florida

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations and political aspects related to Florida

    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
    Israeli
    -1.33
     IDF
    -1.32
    Israel
    -1.31
     Israelis
    -1.28
    anyahu
    -1.24
     Israeli
    -1.15
    Palestinian
    -1.14
     Israel
    -1.13
     Netanyahu
    -1.12
    Palest
    -1.12
    POSITIVE LOGITS
     Florida
    2.27
    Florida
    2.19
     Fla
    2.06
     Gators
    1.92
     Tampa
    1.91
     Semin
    1.90
     Brow
    1.86
     Saras
    1.79
    Fla
    1.78
     Jacksonville
    1.78
    Activations Density 0.342%

    No Known Activations