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. 8863
    Prev
    Next
    INDEX
    Explanations

    locations or addresses, specifically streets and avenues

    oai_token-act-pair · gpt-3.5-turbo

    geographic locations and addresses

    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
    ozy
    -0.69
     legions
    -0.68
     Legions
    -0.67
    erity
    -0.65
    ipedia
    -0.64
     Clash
    -0.63
    icter
    -0.62
    theless
    -0.62
    acity
    -0.62
    arious
    -0.60
    POSITIVE LOGITS
     NW
    1.28
     NE
    1.15
     Northeast
    1.05
     SW
    1.02
     Northwest
    0.99
     Southeast
    0.99
     SE
    0.95
     East
    0.94
     Suite
    0.92
     Southwest
    0.90
    Activations Density 0.071%

    No Known Activations