© 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. 3-RES-JB
    11. 17673
    Prev
    Next
    INDEX
    Explanations

    mentions of political positions or titles, particularly "Secretary."

    oai_token-act-pair · gpt-3.5-turbo

    references to government officials, specifically secretaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    river
    -0.74
    eros
    -0.73
    amaz
    -0.72
    rights
    -0.71
     brim
    -0.67
    users
    -0.65
    ones
    -0.65
    emp
    -0.65
    orsi
    -0.63
    asca
    -0.63
    POSITIVE LOGITS
     Secretary
    1.15
    Secretary
    0.94
     secretary
    0.88
    osate
    0.79
     General
    0.77
     Assistant
    0.75
     secretaries
    0.74
    IAL
    0.74
    ially
    0.74
     Lyndon
    0.72
    Activations Density 0.014%

    No Known Activations