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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 10568
    Prev
    Next
    INDEX
    Explanations

    locations or places, especially in the southern United States

    oai_token-act-pair · gpt-3.5-turbo

    geographic locations, particularly cities and states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Milan
    -1.01
     Israelis
    -0.98
     Ãĸ
    -0.97
     Droid
    -0.94
     droid
    -0.91
     Hungarian
    -0.91
    ás
    -0.89
     UID
    -0.89
    án
    -0.89
     Zi
    -0.88
    POSITIVE LOGITS
     Tennessee
    1.66
     Charleston
    1.64
     Alabama
    1.59
     Kentucky
    1.56
     Louisiana
    1.50
     Asheville
    1.48
    Alabama
    1.48
    Tenn
    1.47
     Chattanooga
    1.46
     Georgia
    1.46
    Activations Density 0.419%

    No Known Activations