© 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. 9-RES-JB
    11. 2347
    Prev
    Next
    INDEX
    Explanations

    percentage values and financial terms

    oai_token-act-pair · gpt-3.5-turbo

    quantitative information, specifically success rates and percentages

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    devices
    -0.75
     innumerable
    -0.69
    etheus
    -0.68
    pecially
    -0.68
    lude
    -0.63
     thousands
    -0.62
     itiner
    -0.61
    interstitial
    -0.59
    dates
    -0.59
    cules
    -0.57
    POSITIVE LOGITS
    ococ
    0.85
    Percent
    0.83
     variance
    0.81
     rate
    0.81
    %,
    0.78
     apiece
    0.77
     polled
    0.77
     chance
    0.77
     satisfaction
    0.76
     (%
    0.76
    Activations Density 0.268%

    No Known Activations