© 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. 1-RES-JB
    6. 11619
    Prev
    Next
    INDEX
    Explanations

    references to or mentions of the Palestinian leader Yasser Arafat

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Palestinian."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    paio
    -0.91
    aunder
    -0.90
    lasses
    -0.88
    ickle
    -0.82
    orgetown
    -0.81
    xus
    -0.80
    peror
    -0.80
    gling
    -0.80
    laus
    -0.79
    ocket
    -0.79
    POSITIVE LOGITS
    Palestinian
    1.11
     Palestinian
    1.04
     Territories
    1.02
    Israeli
    0.93
     Palestinians
    0.91
     Authority
    0.91
     refugees
    0.88
     Palestine
    0.85
     Arabs
    0.85
    Palest
    0.84
    Activations Density 0.009%

    No Known Activations