Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 23677
    Prev
    Next
    INDEX
    Explanations

    words related to locations, specifically related to "Sonoma County."

    oai_token-act-pair · gpt-3.5-turbo

    names of locations, particularly counties and regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sheet
    -0.90
    tumblr
    -0.84
    udeb
    -0.80
     embr
    -0.80
    ngth
    -0.77
    esp
    -0.74
    Ott
    -0.73
    hran
    -0.70
    breaks
    -0.70
    dyl
    -0.69
    POSITIVE LOGITS
     County
    2.32
     Valley
    1.60
     county
    1.50
     counties
    1.46
     COUNTY
    1.45
     Township
    1.36
     Springs
    1.35
     Island
    1.28
     Falls
    1.24
     Parish
    1.21
    Activations Density 0.178%

    No Known Activations