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

    Neuronpedia

    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. 13930
    Prev
    Next
    INDEX
    Explanations

    specific regional references and geospatial relationships

    oai_token-act-pair · gpt-3.5-turbo

    specific events or situations involving significant legal or political implications

    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
     Canaver
    -0.85
     Sven
    -0.84
    Tesla
    -0.82
    ileaks
    -0.80
    Steven
    -0.80
     Robots
    -0.79
     Hermes
    -0.79
    nikov
    -0.77
    iesel
    -0.77
     Turing
    -0.76
    POSITIVE LOGITS
     region
    1.71
     regions
    1.70
     Areas
    1.69
     areas
    1.61
     area
    1.59
     Area
    1.58
     Region
    1.58
     districts
    1.51
     Regions
    1.50
     zones
    1.49
    Activations Density 0.551%

    No Known Activations