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. 18484
    Prev
    Next
    INDEX
    Explanations

    words related to announcements and verbal declarations

    oai_token-act-pair · gpt-3.5-turbo

    references to measurement units, particularly those related to fluid ounces

    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
    acea
    -1.00
    otherapy
    -0.87
    itaire
    -0.83
    Downloadha
    -0.80
    gew
    -0.75
    ocr
    -0.72
    icum
    -0.71
    iciency
    -0.70
    omon
    -0.70
    ocide
    -0.69
    POSITIVE LOGITS
    ment
    1.02
    ments
    0.98
    theless
    0.79
    sburg
    0.79
    rers
    0.78
    prise
    0.78
    MENTS
    0.74
    ounce
    0.72
    prises
    0.71
    mare
    0.71
    Activations Density 0.049%

    No Known Activations