© 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. 11-RES-JB
    11. 20697
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Obama."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Obama" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itionally
    -0.76
     Cth
    -0.75
    ounge
    -0.73
    amel
    -0.68
    auri
    -0.67
     Kok
    -0.67
    finder
    -0.66
    asma
    -0.64
     Newcastle
    -0.64
     Edinburgh
    -0.64
    POSITIVE LOGITS
     administration
    1.14
     Administration
    1.08
    Care
    1.04
    Obama
    0.99
    administ
    0.90
     appoint
    0.89
     Admin
    0.88
     Obama
    0.86
     administrations
    0.86
    omics
    0.86
    Activations Density 0.059%

    No Known Activations