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. 0-RES-JB
    6. 9343
    Prev
    Next
    INDEX
    Explanations

    places or locations named "San"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the city "San"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tons
    -0.89
     owl
    -0.85
    oglobin
    -0.77
     Logged
    -0.75
     [*]
    -0.75
    colour
    -0.73
    atonin
    -0.68
     MEP
    -0.68
    ONS
    -0.67
    raught
    -0.67
    POSITIVE LOGITS
     San
    3.45
    San
    2.98
     SAN
    2.08
    SAN
    1.97
     Sacramento
    1.89
     Palo
    1.85
     Los
    1.79
     Oakland
    1.76
     san
    1.76
     Santa
    1.69
    Activations Density 0.015%

    No Known Activations