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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 10604
    Prev
    Next
    INDEX
    Explanations

    references to specific legal terms

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "Just" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    luster
    -0.81
    existent
    -0.66
    glomer
    -0.64
     Prelude
    -0.63
    externalActionCode
    -0.61
     challeng
    -0.60
    ught
    -0.59
     quo
    -0.59
     gland
    -0.58
     Reincarn
    -0.57
    POSITIVE LOGITS
    ifications
    1.37
    ices
    1.24
    ifiable
    1.23
    ified
    1.16
    ification
    1.14
    icia
    1.06
    ifi
    1.03
    iciary
    1.00
    itia
    1.00
    ifiers
    1.00
    Activations Density 0.066%

    No Known Activations