© 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. 7-RES-JB
    11. 9898
    Prev
    Next
    INDEX
    Explanations

    references to religious or prestigious titles, specifically focusing on the term "Pri" and variations such as "Priest" and "Prius."

    oai_token-act-pair · gpt-3.5-turbo

    references to prestigious awards or honors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -1.07
    schild
    -0.78
    ding
    -0.71
    ded
    -0.69
     Wink
    -0.67
     Leilan
    -0.67
    icago
    -0.64
     dred
    -0.62
    ç¥ŀ
    -0.61
     HELL
    -0.60
    POSITIVE LOGITS
    ests
    1.28
    zes
    1.10
    eties
    1.08
    ety
    1.06
    etary
    1.03
    esses
    1.00
    Ľ
    0.88
    heed
    0.87
    vy
    0.87
    eur
    0.85
    Activations Density 0.018%

    No Known Activations