© 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 EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 1212
    Prev
    Next
    INDEX
    Explanations

    locations and proper nouns, specifically related to the city of San Jose

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of San Jose and surrounding regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dys
    -0.66
     favour
    -0.65
    matter
    -0.65
    sworth
    -0.65
    èĢ
    -0.64
     stret
    -0.63
    letter
    -0.63
    ãĤ¯
    -0.62
     mete
    -0.62
    ACY
    -0.61
    POSITIVE LOGITS
     Earthqu
    0.97
     Valley
    0.90
     County
    0.89
     Unified
    0.87
     Padres
    0.80
     Rapids
    0.79
    atchewan
    0.79
     Springs
    0.79
     Mountains
    0.75
    Gas
    0.73
    Activations Density 0.049%

    No Known Activations