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. 15544
    Prev
    Next
    INDEX
    Explanations

    mentions of locations and events related to San Diego

    oai_token-act-pair · gpt-3.5-turbo

    locations and terms specifically related to San Diego

    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
    enburg
    -0.78
    ijah
    -0.77
    bley
    -0.72
    bringer
    -0.69
    esley
    -0.66
    dr
    -0.64
    Bir
    -0.64
    enstein
    -0.63
    adj
    -0.62
    mercial
    -0.62
    POSITIVE LOGITS
     Padres
    1.46
     Chargers
    1.30
     County
    1.23
     Unified
    1.23
     Earthqu
    1.15
     Comic
    1.11
     Sharks
    0.94
     State
    0.93
     Diego
    0.92
     Costa
    0.91
    Activations Density 0.051%

    No Known Activations