© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 0-RES-JB
    11. 8282
    Prev
    Next
    INDEX
    Explanations

    references to individuals holding positions of authority or leadership, specifically the position of "Chair."

    oai_token-act-pair · gpt-3.5-turbo

    the term "Chair" used in various contexts, indicating leadership or position in committees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     evapor
    -0.75
    ="#
    -0.69
    inventoryQuantity
    -0.67
     strip
    -0.67
     rehab
    -0.67
     scouting
    -0.66
     cort
    -0.59
    ied
    -0.59
     zip
    -0.59
     passer
    -0.58
    POSITIVE LOGITS
     Chair
    3.96
    Chair
    2.47
     Chairman
    2.16
     chair
    2.06
    chair
    1.72
     chairs
    1.63
     Speaker
    1.52
     chairman
    1.45
    chairs
    1.42
     Desk
    1.32
    Activations Density 0.005%

    No Known Activations