© 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
    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. 20101
    Prev
    Next
    INDEX
    Explanations

    mentions of the country "Cyprus"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Cyprus

    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
     loops
    -0.78
     portals
    -0.77
     trainers
    -0.76
     retweet
    -0.75
    quickShipAvailable
    -0.75
    querque
    -0.73
    bart
    -0.73
     humor
    -0.72
     mocking
    -0.72
    keyes
    -0.70
    POSITIVE LOGITS
     Cyprus
    2.89
     Syn
    1.76
     Nic
    1.21
     Syri
    1.18
     Christine
    1.15
    prus
    1.07
     Tud
    1.05
     Canon
    1.05
     Byzantine
    1.03
     Tos
    1.02
    Activations Density 0.037%

    No Known Activations