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. 9-RES-JB
    6. 12026
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Aiyar"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of a specific character or name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gutenberg
    -0.71
    ITY
    -0.67
     Annotations
    -0.66
    Assembly
    -0.66
     unfocusedRange
    -0.61
    ilater
    -0.56
     perpet
    -0.56
     Mayhem
    -0.55
     Hurricanes
    -0.55
     magnification
    -0.54
    POSITIVE LOGITS
    uki
    1.12
    ield
    1.03
    yah
    1.00
    akov
    0.98
    ahu
    0.98
    ielding
    0.98
    arb
    0.97
    outh
    0.95
    azaki
    0.94
    uan
    0.94
    Activations Density 0.055%

    No Known Activations