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. 3-RES-JB
    6. 10201
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations, particularly focusing on the city of Istanbul

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of Istanbul and its surrounding locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pring
    -0.87
    morph
    -0.73
    vol
    -0.72
    drawn
    -0.72
    ceed
    -0.70
    cess
    -0.70
    cor
    -0.70
    INAL
    -0.68
    lear
    -0.68
    administ
    -0.68
    POSITIVE LOGITS
     Istanbul
    0.91
     Lumpur
    0.91
     mosqu
    0.83
    istani
    0.80
     Airlines
    0.80
     Turks
    0.75
    ophobic
    0.75
     Ankara
    0.74
     Emir
    0.74
     citiz
    0.73
    Activations Density 0.007%

    No Known Activations