© 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. 11-RES-JB
    11. 20575
    Prev
    Next
    INDEX
    Explanations

    references to locations or regions

    oai_token-act-pair · gpt-3.5-turbo

    references to residents or community members in a geographical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     centrif
    -0.84
    arya
    -0.62
    xual
    -0.59
     embr
    -0.59
    DragonMagazine
    -0.59
    tics
    -0.57
    attribute
    -0.57
     scientist
    -0.57
     physic
    -0.56
    translation
    -0.56
    POSITIVE LOGITS
     Sask
    1.36
     Winnipeg
    1.26
     Mississ
    1.25
     Spokane
    1.24
     Vancouver
    1.24
     Halifax
    1.24
     Edmonton
    1.23
     Ontario
    1.23
     Burlington
    1.22
     Minneapolis
    1.22
    Activations Density 0.656%

    No Known Activations