© 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. 11-RES-JB
    11. 12879
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial or economic matters, such as government actions, industry impacts, prices, and agreements

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their associated frequencies in the text

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     favor
    -0.94
     favoring
    -0.93
     favorably
    -0.89
     defenses
    -0.87
     metic
    -0.86
     categorized
    -0.86
     willfully
    -0.84
     utilizing
    -0.83
     favored
    -0.83
     subsidized
    -0.83
    POSITIVE LOGITS
    Topics
    2.00
    Mr
    1.82
    Shape
    1.76
    Ms
    1.65
    Analysis
    1.65
    Image
    1.64
    However
    1.62
    Media
    1.55
    Labour
    1.55
    media
    1.52
    Activations Density 0.215%

    No Known Activations