© 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. 10-RES-JB
    11. 6054
    Prev
    Next
    INDEX
    Explanations

    organizations, agencies, and initiatives related to law, defense, education, and finance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal, regulatory, and enforcement frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     brushes
    -0.72
     cyn
    -0.65
     wheels
    -0.65
    wcs
    -0.64
     skiing
    -0.63
     showc
    -0.62
    dfx
    -0.61
    ozyg
    -0.61
    selage
    -0.60
    inventoryQuantity
    -0.59
    POSITIVE LOGITS
     Organization
    0.86
     Fund
    0.83
     Association
    0.81
     Act
    0.80
     Reporting
    0.78
     Program
    0.76
     Project
    0.75
     Initiative
    0.74
     Commission
    0.74
     Center
    0.72
    Activations Density 0.115%

    No Known Activations