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. 10-RES-JB
    6. 19123
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Perry" along with numerical values attached to it, potentially indicating a strong association or importance placed on the name as a keyword in a text corpus

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Perry."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ues
    -0.72
    hent
    -0.68
    aries
    -0.67
    arten
    -0.66
    otine
    -0.65
    ATIONAL
    -0.65
    ged
    -0.63
    iste
    -0.62
    acular
    -0.62
    udic
    -0.61
    POSITIVE LOGITS
    sburg
    0.98
    man
    0.92
    burgh
    0.78
    ns
    0.78
    ipher
    0.77
    utical
    0.74
    grad
    0.74
    bard
    0.74
    idon
    0.74
    mons
    0.74
    Activations Density 0.036%

    No Known Activations