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. 15070
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names, specifically those related to the name "Candle."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "candy" and related terms

    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
    FactoryReloaded
    -0.67
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.66
     pity
    -0.62
     chau
    -0.61
     prepar
    -0.58
    GV
    -0.57
     sight
    -0.57
     nuisance
    -0.56
     disparate
    -0.56
     Progress
    -0.56
    POSITIVE LOGITS
    lest
    1.54
    idates
    1.51
    idate
    1.34
    les
    1.11
    arette
    0.98
    ace
    0.97
    ela
    0.97
    escent
    0.94
    ice
    0.94
    acies
    0.92
    Activations Density 0.027%

    No Known Activations