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. 6839
    Prev
    Next
    INDEX
    Explanations

    phrases related to large quantities of a specific object

    oai_token-act-pair · gpt-3.5-turbo

    the word "ands" and its variations, particularly in contexts that suggest abundance or grouping

    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
    UTION
    -0.75
    TON
    -0.69
    ZZ
    -0.65
    ITAL
    -0.63
    DAY
    -0.63
    GB
    -0.62
    STON
    -0.62
    IOR
    -0.62
    STER
    -0.59
    é¾įå
    -0.59
    POSITIVE LOGITS
    ands
    1.08
    anding
    1.01
    anded
    0.90
    chwitz
    0.88
    sein
    0.84
    andra
    0.83
    aints
    0.82
    ignty
    0.79
    avage
    0.78
    agne
    0.77
    Activations Density 0.018%

    No Known Activations