© 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. 2747
    Prev
    Next
    INDEX
    Explanations

    decades or time periods from the past

    oai_token-act-pair · gpt-3.5-turbo

    references to decades, particularly the 70s, 80s, and 90s, and their associated cultural artifacts

    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
    rollment
    -0.85
    region
    -0.83
    potion
    -0.81
    andum
    -0.81
    REDACTED
    -0.79
    apter
    -0.75
    owship
    -0.73
    Contents
    -0.71
    ledged
    -0.70
    uid
    -0.70
    POSITIVE LOGITS
     nostalgia
    1.16
     classics
    1.14
     sitcom
    1.03
     sensibilities
    0.98
    -'
    0.98
     era
    0.97
     aesthetics
    0.96
     vintage
    0.95
     glam
    0.94
     Era
    0.92
    Activations Density 0.192%

    No Known Activations