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. 11-RES-JB
    6. 2880
    Prev
    Next
    INDEX
    Explanations

    captions or text prompts requesting interaction or verification in online forms

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to verification and authenticity checks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ballard
    -0.53
     Hin
    -0.52
     Loft
    -0.52
     Hick
    -0.50
     tantal
    -0.50
     Bak
    -0.49
     Furious
    -0.49
     flank
    -0.49
     Cass
    -0.49
     Gall
    -0.48
    POSITIVE LOGITS
    ENA
    0.68
    breaker
    0.67
    rina
    0.65
    thumbnails
    0.61
    oxin
    0.61
    ãĥīãĥ©ãĤ´ãĥ³
    0.61
    wcsstore
    0.57
    ically
    0.57
    ierrez
    0.56
    washer
    0.56
    Activations Density 0.021%

    No Known Activations