© 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. 9-RES-JB
    11. 7389
    Prev
    Next
    INDEX
    Explanations

    references to historical events and religious texts

    oai_token-act-pair · gpt-3.5-turbo

    references to religious texts and significant historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terday
    -0.85
    ĻĤ
    -0.84
     nonex
    -0.67
     traumatic
    -0.65
    ĪĴ
    -0.62
    myra
    -0.62
     consumption
    -0.62
     facial
    -0.62
     employment
    -0.61
     matt
    -0.60
    POSITIVE LOGITS
     Room
    1.00
     Gazette
    0.97
     Committee
    0.97
     Awards
    0.95
     Builder
    0.92
     Chamber
    0.92
     Council
    0.91
     Graveyard
    0.89
     Era
    0.89
     Trilogy
    0.87
    Activations Density 0.310%

    No Known Activations