© 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. 8-RES-JB
    11. 14293
    Prev
    Next
    INDEX
    Explanations

    data related to financial numbers and statistics

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and references to financial metrics

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    pard
    -0.70
    lance
    -0.68
    achev
    -0.63
    hole
    -0.63
    speech
    -0.61
    urred
    -0.60
     withdrew
    -0.59
    holes
    -0.59
     hesitated
    -0.59
    aer
    -0.59
    POSITIVE LOGITS
     accommodate
    0.95
    ggles
    0.90
     encompass
    0.86
     include
    0.86
     avoid
    0.86
     compensate
    0.85
     ensure
    0.82
     346
    0.81
     ¥
    0.80
     344
    0.77
    Activations Density 0.087%

    No Known Activations