© 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. 3-RES-JB
    6. 9384
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations, particularly Kuwait

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Kuwait and related geopolitical contexts

    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
    lihood
    -0.84
    BOOK
    -0.80
    66666666
    -0.73
    nings
    -0.72
    ãģ¦
    -0.67
    Else
    -0.66
    MENTS
    -0.66
    Oracle
    -0.64
    MENT
    -0.62
    Ign
    -0.62
    POSITIVE LOGITS
    igon
    0.93
    iya
    0.92
     Airways
    0.91
    ileaks
    0.90
     Kuwait
    0.88
    adian
    0.85
     Arabia
    0.84
    amiya
    0.81
    iyah
    0.78
     Hussein
    0.78
    Activations Density 0.003%

    No Known Activations