© 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. 18272
    Prev
    Next
    INDEX
    Explanations

    locations or scenes where law enforcement or emergency services have been called to

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the" and related phrases indicating locations

    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
    Īè
    -0.88
    govtrack
    -0.83
    ohan
    -0.80
    naire
    -0.78
    opus
    -0.77
    γ
    -0.77
    wart
    -0.76
    [_
    -0.74
    lance
    -0.74
    estro
    -0.74
    POSITIVE LOGITS
     premises
    1.25
     scene
    1.20
     facility
    1.14
     offices
    1.12
     site
    1.12
     mansion
    1.08
     apartment
    1.06
     vicinity
    1.05
     residence
    1.04
     courthouse
    1.02
    Activations Density 0.285%

    No Known Activations