© 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. 8-RES-JB
    11. 1116
    Prev
    Next
    INDEX
    Explanations

    specific location names, especially those related to political figures

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Mar-a-Lago and associated references to Trump

    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
    izabeth
    -0.78
     Confederation
    -0.73
     Chambers
    -0.68
     Cannon
    -0.66
     Finnish
    -0.62
     Borders
    -0.62
     Chop
    -0.57
     breathing
    -0.57
     Flavoring
    -0.56
     dive
    -0.56
    POSITIVE LOGITS
    Lago
    0.83
    lease
    0.81
    bearing
    0.79
    su
    0.78
    lan
    0.78
    shaped
    0.77
    Bu
    0.77
    selection
    0.74
    sized
    0.73
    lab
    0.73
    Activations Density 0.092%

    No Known Activations