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. 15062
    Prev
    Next
    INDEX
    Explanations

    ages or numbers related to measurement or categorization

    oai_token-act-pair · gpt-3.5-turbo

    references to age

    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
    etheless
    -0.85
    IFIED
    -0.75
    pard
    -0.73
    marg
    -0.69
    assets
    -0.66
    SpaceEngineers
    -0.64
    ãĥ¼ãĥ«
    -0.63
    ounced
    -0.63
    nesday
    -0.62
    mes
    -0.62
    POSITIVE LOGITS
    llan
    1.29
    llo
    1.13
    lla
    0.93
    ments
    0.92
    utic
    0.86
    utics
    0.83
    oline
    0.80
     Mutant
    0.78
    llular
    0.77
    y
    0.76
    Activations Density 0.055%

    No Known Activations