© 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. 0-RES-JB
    11. 13507
    Prev
    Next
    INDEX
    Explanations

    locations or proper nouns containing the word "Bod", as well as potential misspellings or variations of "dodgy"

    oai_token-act-pair · gpt-3.5-turbo

    specific geographical locations and the term "dodgy"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ippi
    -0.85
     colonization
    -0.73
     Patton
    -0.72
     Garrison
    -0.71
    archs
    -0.66
     Marshal
    -0.65
     intrigue
    -0.65
     Confederacy
    -0.64
    iani
    -0.64
    osi
    -0.64
    POSITIVE LOGITS
     Bod
    2.11
     dod
    1.81
    edin
    1.65
     Bend
    1.43
     bod
    1.26
     Samar
    1.08
     Ox
    1.04
    Ox
    1.01
    Mom
    0.99
     Moment
    0.98
    Activations Density 0.059%

    No Known Activations