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. 10315
    Prev
    Next
    INDEX
    Explanations

    names or titles of world leaders

    oai_token-act-pair · gpt-3.5-turbo

    references to political leaders, specifically presidents

    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
    opter
    -0.85
    eros
    -0.82
    aughs
    -0.73
    andem
    -0.73
    asca
    -0.71
    ritch
    -0.70
    ourcing
    -0.66
    Scot
    -0.65
    aylor
    -0.64
    ogene
    -0.64
    POSITIVE LOGITS
     Mahmoud
    1.00
     Bashar
    0.91
     negotiator
    0.89
     Jinping
    0.89
     Viktor
    0.85
     Hassan
    0.82
     Mahm
    0.77
     Putin
    0.76
     Tayyip
    0.76
     bloc
    0.75
    Activations Density 0.087%

    No Known Activations