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. 7-RES-JB
    6. 10191
    Prev
    Next
    INDEX
    Explanations

    instances of the word "show"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "show."

    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
    kson
    -0.65
     retaining
    -0.63
    tymology
    -0.62
    ades
    -0.62
    assic
    -0.62
     proceeding
    -0.61
    nian
    -0.60
     captcha
    -0.59
    oldown
    -0.58
    ataka
    -0.57
    POSITIVE LOGITS
    biz
    1.14
    alter
    1.03
    manship
    0.99
    ered
    0.91
    runners
    0.86
    downs
    0.83
    amy
    0.78
    boat
    0.76
    rooms
    0.75
    runner
    0.74
    Activations Density 0.064%

    No Known Activations