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. 362
    Prev
    Next
    INDEX
    Explanations

    time-related expressions, such as weeks, years, months, and hours

    oai_token-act-pair · gpt-3.5-turbo

    instances of Pokémon character descriptions

    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
     Mellon
    -0.61
    ersen
    -0.58
    kef
    -0.58
     Wr
    -0.57
     exha
    -0.55
     Borders
    -0.55
     Jagu
    -0.53
     Gateway
    -0.53
     Cantor
    -0.53
     kindred
    -0.52
    POSITIVE LOGITS
     ago
    0.80
    Depth
    0.68
     >=
    0.67
    Menu
    0.64
    view
    0.64
    cloud
    0.63
     ][
    0.63
    coin
    0.62
    Joined
    0.62
    elta
    0.62
    Activations Density 0.058%

    No Known Activations