© 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. 2-RES-JB
    11. 16010
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "bureau."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to government agencies or organizations, particularly with the word "bureau" and its variations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dash
    -0.72
    artifacts
    -0.70
    VID
    -0.70
    igo
    -0.67
    DonaldTrump
    -0.64
    ebook
    -0.64
    allows
    -0.63
    forcing
    -0.63
    tackle
    -0.62
    docker
    -0.62
    POSITIVE LOGITS
     bureau
    1.11
    ureau
    0.86
    oreal
    0.77
     Bureau
    0.75
     informant
    0.72
     correspondent
    0.70
     clerk
    0.68
     tipped
    0.68
     selector
    0.67
     clerks
    0.66
    Activations Density 0.003%

    No Known Activations