© 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. 4-RES-JB
    11. 699
    Prev
    Next
    INDEX
    Explanations

    mentions of historical figures, specifically focusing on Theodore Roosevelt

    oai_token-act-pair · gpt-3.5-turbo

    references to historical figures, particularly Theodore Roosevelt

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

    No Comments

    Negative Logits
    Loading
    -0.69
    Buzz
    -0.68
    OIL
    -0.68
    birth
    -0.65
    gans
    -0.64
    places
    -0.64
    points
    -0.63
    shapeshifter
    -0.62
    ebook
    -0.61
    respect
    -0.61
    POSITIVE LOGITS
     Roosevelt
    1.17
     Theodore
    0.97
    sonian
    0.86
    itus
    0.83
     Herz
    0.81
    sson
    0.80
    eteenth
    0.79
    \\\\\\\\
    0.77
    ufact
    0.75
     Sturgeon
    0.74
    Activations Density 0.011%

    No Known Activations