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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1098
    Prev
    Next
    INDEX
    Explanations

    rituals, traditional practices, and significant customs

    oai_token-act-pair · gpt-3.5-turbo

    references to rites of passage and significant cultural rituals

    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
     neoc
    -0.78
     McKenzie
    -0.77
     Monaco
    -0.76
    monitor
    -0.75
    DK
    -0.74
     Robertson
    -0.74
    raq
    -0.71
    enegger
    -0.71
     dynam
    -0.70
     Garrison
    -0.70
    POSITIVE LOGITS
     rite
    2.21
     Rite
    2.17
     unheard
    1.50
     rites
    1.50
     Loll
    1.43
     Rak
    1.31
     Reign
    1.15
     rude
    1.12
     Rollins
    1.08
     Urs
    0.97
    Activations Density 0.075%

    No Known Activations