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. 4549
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific phrase or term "Bon" with some variations in formatting

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "Bon" in various contexts

    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
    INAL
    -0.67
    ODE
    -0.65
    REAM
    -0.56
    ¥
    -0.55
     Ethics
    -0.55
    DonaldTrump
    -0.54
     proofs
    -0.53
    UX
    -0.53
    ELD
    -0.52
     Redux
    -0.52
    POSITIVE LOGITS
    anza
    1.28
    kers
    1.13
    obos
    1.09
    obo
    1.07
    eless
    1.03
    zai
    0.99
    nie
    0.98
    bon
    0.98
    anz
    0.98
    hom
    0.96
    Activations Density 0.029%

    No Known Activations