© 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. 0-RES-JB
    11. 10450
    Prev
    Next
    INDEX
    Explanations

    mentions or references to specific locations such as towns and cities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations associated with significant events like protests or tragedies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adian
    -0.77
     lev
    -0.71
     tender
    -0.69
     mage
    -0.69
     pad
    -0.68
    osi
    -0.67
     Limit
    -0.66
    ido
    -0.66
     hier
    -0.65
    Production
    -0.65
    POSITIVE LOGITS
     Charlottesville
    3.61
     Newtown
    2.25
    ottesville
    1.93
     Ferguson
    1.56
     Fukushima
    1.55
     Chattanooga
    1.45
     Charleston
    1.39
     Sochi
    1.38
    erguson
    1.34
     Benghazi
    1.33
    Activations Density 0.025%

    No Known Activations