© 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. 11-RES-JB
    11. 10283
    Prev
    Next
    INDEX
    Explanations

    data related to states and percentages

    oai_token-act-pair · gpt-3.5-turbo

    mentions of states and their related statistics or demographics

    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
     behavi
    -0.79
    EStreamFrame
    -0.78
    Development
    -0.73
    DragonMagazine
    -0.72
    ãĤ¤ãĥĪ
    -0.68
    sbm
    -0.66
     glim
    -0.64
    fff
    -0.64
    zza
    -0.63
    Ãį
    -0.63
    POSITIVE LOGITS
     Pennsylvania
    1.72
     Illinois
    1.71
     Rhode
    1.69
     Nevada
    1.69
     Nebraska
    1.68
     Wisconsin
    1.67
     Connecticut
    1.67
     Maryland
    1.66
     Wyoming
    1.66
     Montana
    1.65
    Activations Density 0.134%

    No Known Activations