© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 21134
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific geographical location, Taksim Square

    oai_token-act-pair · gpt-3.5-turbo

    references to the Taksim Square

    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
    ãĥ£
    -0.71
    âĸ¬
    -0.63
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.61
     Bapt
    -0.60
     Kitty
    -0.59
    alcohol
    -0.59
    SHIP
    -0.58
     Weasley
    -0.58
     Unle
    -0.58
     Bulldogs
    -0.58
    POSITIVE LOGITS
    aks
    1.08
    andr
    1.06
    ongs
    0.89
    udo
    0.88
    ame
    0.85
    ucker
    0.85
    unta
    0.84
    ames
    0.84
    akes
    0.83
    oup
    0.82
    Activations Density 0.009%

    No Known Activations