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. 5-RES-JB
    6. 24556
    Prev
    Next
    INDEX
    Explanations

    text prompts directing users to scroll for more content

    oai_token-act-pair · gpt-3.5-turbo

    instances of "Scroll" followed by a number, indicating prompts for user interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤº
    -0.86
    roman
    -0.76
    inventoryQuantity
    -0.74
    venge
    -0.66
    ãĥĨãĤ£
    -0.61
    peak
    -0.59
    centered
    -0.58
    iHUD
    -0.56
     Mehran
    -0.56
    ItemImage
    -0.56
    POSITIVE LOGITS
    ificant
    0.93
     Scroll
    0.83
    ancies
    0.81
    itzer
    0.78
    Scroll
    0.78
    abulary
    0.78
    ahead
    0.76
    mares
    0.75
    ancy
    0.73
    scroll
    0.72
    Activations Density 0.005%

    No Known Activations