© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8809
    Prev
    Next
    INDEX
    Explanations

    mentions of museums and specific places or institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to various museums and their subjects

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    inion
    -0.77
     blocker
    -0.76
     blockers
    -0.75
    ĪĴ
    -0.74
     stride
    -0.71
     proxy
    -0.70
    Downloadha
    -0.70
     regress
    -0.69
     accelerator
    -0.67
     multiplier
    -0.67
    POSITIVE LOGITS
     Contemporary
    1.08
     History
    0.99
     Classics
    0.97
     Modern
    0.91
     Photography
    0.91
     Antiqu
    0.90
     Anthropology
    0.90
     Divinity
    0.87
     Computing
    0.87
     Errors
    0.83
    Activations Density 0.114%

    No Known Activations