Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19032
    Prev
    Next
    INDEX
    Explanations

    acronyms or words in ALL CAPS

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "UST" and its variations, indicating a focus on something related to Austin, Texas

    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
    perty
    -0.63
    Kit
    -0.58
     Bundy
    -0.57
    stocks
    -0.57
    kefeller
    -0.56
     bubble
    -0.56
     Dug
    -0.56
    ned
    -0.56
    bo
    -0.55
    etheless
    -0.54
    POSITIVE LOGITS
    rations
    1.21
    rated
    1.20
    rious
    1.15
    rating
    1.14
    ral
    1.13
    rator
    1.12
    rine
    1.09
    rans
    1.07
    ained
    1.06
    rian
    1.04
    Activations Density 0.041%

    No Known Activations