© 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. 9779
    Prev
    Next
    INDEX
    Explanations

    references to specific geographic locations - in this case, the mention of locations related to the Israeli-Palestinian conflict

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Israeli" in various contexts related to conflict and military actions

    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
    mson
    -1.03
    aunder
    -0.99
    mble
    -0.85
    ĸļ
    -0.83
    utic
    -0.82
    ramid
    -0.81
    rencies
    -0.78
    orsche
    -0.78
    iddler
    -0.77
    hematic
    -0.77
    POSITIVE LOGITS
     Israeli
    0.98
    Israeli
    0.95
     Israelis
    0.94
    apolis
    0.86
     embassy
    0.86
    Palestinian
    0.85
     Netanyahu
    0.82
     Jews
    0.82
     Aviv
    0.81
    Israel
    0.81
    Activations Density 0.016%

    No Known Activations