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. 2091
    Prev
    Next
    INDEX
    Explanations

    words related to locations, especially focusing on the city of San Francisco

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of San Francisco

    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
    •ans
    #1 activation: 51.73

    No Comments

    Negative Logits
     Jinn
    -0.66
     adjud
    -0.61
     Neph
    -0.59
     Avenger
    -0.58
     Machina
    -0.57
     Naval
    -0.56
     Siren
    -0.56
     Izan
    -0.55
     expectancy
    -0.55
    weapons
    -0.55
    POSITIVE LOGITS
    isco
    1.15
    ruary
    0.83
    furt
    0.75
    ça
    0.72
    bees
    0.72
    士
    0.68
    rance
    0.68
    fur
    0.66
    ais
    0.65
    cest
    0.65
    Activations Density 0.047%

    No Known Activations