© 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 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. 3320
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Southern."

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Southern" in various contexts

    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
    awaru
    -0.86
    acl
    -0.75
    uers
    -0.68
    haar
    -0.68
    aday
    -0.67
    ifice
    -0.67
    ason
    -0.67
    hya
    -0.66
    hig
    -0.66
    ahon
    -0.65
    POSITIVE LOGITS
     Hemisphere
    1.31
     hemisphere
    1.08
     Poverty
    1.06
     California
    0.99
     Methodist
    0.91
    most
    0.91
     Isles
    0.89
     Liberties
    0.88
     Airlines
    0.87
     Californ
    0.87
    Activations Density 0.025%

    No Known Activations