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. 2-RES-JB
    6. 3593
    Prev
    Next
    INDEX
    Explanations

    references to locations in the Middle East, specifically related to Iran and the Persian Gulf

    oai_token-act-pair · gpt-3.5-turbo

    references to the Persian Gulf and related historical or geographical entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eals
    -0.95
    elling
    -0.87
    illard
    -0.78
    enez
    -0.78
    aping
    -0.77
    ainers
    -0.77
    aped
    -0.77
    burse
    -0.76
    oldemort
    -0.75
    redo
    -0.75
    POSITIVE LOGITS
     Gulf
    1.05
     Persian
    1.03
     Grip
    0.75
     sensibilities
    0.74
    merga
    0.74
     appe
    0.73
     Quarter
    0.73
     rug
    0.73
     fries
    0.72
     Arabian
    0.70
    Activations Density 0.008%

    No Known Activations