© 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. 7-RES-JB
    11. 13732
    Prev
    Next
    INDEX
    Explanations

    locations where actions are taking place

    oai_token-act-pair · gpt-3.5-turbo

    references to locations where events are taking place, particularly protests or gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oleon
    -0.87
    XX
    -0.78
    Percent
    -0.77
    anche
    -0.76
    oka
    -0.75
    ppe
    -0.75
    aler
    -0.72
    orne
    -0.69
    ulous
    -0.69
    etti
    -0.68
    POSITIVE LOGITS
     Staples
    0.77
     Sunset
    0.72
     town
    0.71
     patio
    0.70
    eatures
    0.70
     Stamford
    0.70
     perimeter
    0.70
     midnight
    0.69
     Borders
    0.68
     parliament
    0.67
    Activations Density 0.035%

    No Known Activations