© 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. 12160
    Prev
    Next
    INDEX
    Explanations

    keywords related to political events, specifically presidential inaugurations

    oai_token-act-pair · gpt-3.5-turbo

    references related to official ceremonies and inaugurations

    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
    oxin
    -0.87
    finder
    -0.82
    aceutical
    -0.77
    idges
    -0.74
    edin
    -0.73
    ouri
    -0.72
    bane
    -0.72
    Soft
    -0.70
    atem
    -0.68
    esian
    -0.67
    POSITIVE LOGITS
     ceremony
    1.86
     ceremonies
    1.74
     festivities
    1.39
     Cere
    1.37
     banquet
    1.32
     parade
    1.31
     celebrations
    1.26
     celebration
    1.25
     speeches
    1.20
     procession
    1.19
    Activations Density 0.115%

    No Known Activations