Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 10608
    Prev
    Next
    INDEX
    Explanations

    references to the Arab world

    oai_token-act-pair · gpt-3.5-turbo

    references to "Arab" in various 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
    ertodd
    -0.99
    paio
    -0.83
    vg
    -0.81
    uden
    -0.81
    cise
    -0.76
    pload
    -0.75
    utherford
    -0.75
    aminer
    -0.74
     McConnell
    -0.74
     Gutenberg
    -0.73
    POSITIVE LOGITS
     Arab
    0.98
     Arabs
    0.88
     princes
    0.78
     Aram
    0.78
    esque
    0.74
     Nights
    0.73
     kingdoms
    0.73
     regimes
    0.72
    akh
    0.72
     Empires
    0.72
    Activations Density 0.007%

    No Known Activations