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. 7-RES-JB
    6. 24415
    Prev
    Next
    INDEX
    Explanations

    phrases containing the name "Aiyar"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Aiyar."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĹ¼
    -0.74
    IBLE
    -0.71
    wcs
    -0.71
    mint
    -0.70
     Hurricanes
    -0.67
    ufact
    -0.66
    ãĥ¬
    -0.64
     multicultural
    -0.60
    insula
    -0.59
     Gutenberg
    -0.59
    POSITIVE LOGITS
    yah
    1.20
    yy
    1.01
    adh
    0.99
    azaki
    0.99
    ahu
    0.98
    ielding
    0.93
    atana
    0.93
    ota
    0.93
    oji
    0.92
    akov
    0.91
    Activations Density 0.024%

    No Known Activations