© 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 EvalsExportsinterp-engineNEWAPI 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. 1-RES-JB
    11. 9581
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to politics and current affairs

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Washington."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    order
    -0.74
    ordering
    -0.69
    gger
    -0.69
    lass
    -0.63
    compan
    -0.62
    otropic
    -0.62
    aster
    -0.61
    hang
    -0.60
    odic
    -0.60
    asters
    -0.60
    POSITIVE LOGITS
    ASHINGTON
    1.37
    WASHINGTON
    1.35
    aukee
    1.03
    Washington
    0.95
    ukong
    0.95
    ashtra
    0.93
     DC
    0.88
    ITED
    0.87
    DERR
    0.86
    sburgh
    0.86
    Activations Density 0.005%

    No Known Activations