© 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. 22853
    Prev
    Next
    INDEX
    Explanations

    references to the location "Los Angeles"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Los Angeles."

    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
    ebook
    -0.78
    BOOK
    -0.74
     miscarriage
    -0.73
    stroke
    -0.72
    ICLE
    -0.71
    OPLE
    -0.66
    displayText
    -0.65
     tremend
    -0.64
    mble
    -0.63
     basket
    -0.63
    POSITIVE LOGITS
     Angeles
    1.61
     Alam
    1.05
     Santos
    0.97
    ction
    0.92
    ites
    0.89
    ctions
    0.89
     ANGEL
    0.86
     Aires
    0.86
     Lumpur
    0.85
     Rey
    0.84
    Activations Density 0.015%

    No Known Activations