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. 11-RES-JB
    6. 8174
    Prev
    Next
    INDEX
    Explanations

    mentions of locations or entities associated with the city of Portland

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations, organizations, and events in Portland, Oregon

    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
     Tehran
    -1.32
    Iran
    -1.19
     Iranians
    -1.13
     Hezbollah
    -1.10
     Iran
    -1.10
     Houth
    -1.09
     Iranian
    -1.07
     Cyrus
    -1.02
    ollah
    -1.02
     Shia
    -1.01
    POSITIVE LOGITS
     Oregon
    2.33
     Portland
    2.23
    Portland
    2.19
    Oregon
    2.17
     Timbers
    1.73
     Ore
    1.56
     Ducks
    1.55
     Cascade
    1.55
     Blazers
    1.55
     Eugene
    1.50
    Activations Density 0.278%

    No Known Activations