© 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. 8-RES-JB
    11. 7744
    Prev
    Next
    INDEX
    Explanations

    mentions of the United States Navy

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Navy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oned
    -0.78
    DonaldTrump
    -0.73
     DRM
    -0.69
     Gree
    -0.66
    upon
    -0.66
     Gandhi
    -0.64
    olkien
    -0.64
    IBLE
    -0.64
    aphael
    -0.64
     DEAD
    -0.64
    POSITIVE LOGITS
     SEAL
    1.32
     Yard
    1.09
     Seal
    0.98
     sailor
    0.92
    boats
    0.90
    boat
    0.89
    odon
    0.89
     Sea
    0.86
     Fisheries
    0.86
    ategory
    0.85
    Activations Density 0.025%

    No Known Activations