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

    Neuronpedia

    Jacobian LensNEW
    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. 21209
    Prev
    Next
    INDEX
    Explanations

    references to percentages or numbers in the financial context

    oai_token-act-pair · gpt-3.5-turbo

    references to percentages related to wealth inequality and economic data

    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
    ãĤ©
    -0.75
    Ö¼
    -0.71
    IRT
    -0.71
     compr
    -0.69
    Merit
    -0.65
    ¯¯
    -0.65
    åİ
    -0.64
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.64
     tyr
    -0.63
     unden
    -0.63
    POSITIVE LOGITS
     increments
    0.93
    uary
    0.86
    iles
    0.84
    ual
    0.79
    uation
    0.78
    imet
    0.75
    ennial
    0.75
     GDP
    0.75
    ancy
    0.72
    acre
    0.72
    Activations Density 0.064%

    No Known Activations