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. 11477
    Prev
    Next
    INDEX
    Explanations

    phrases indicating emphasis or importance

    oai_token-act-pair · gpt-3.5-turbo

    the word "especially" and its variations, indicating emphasis or significance on particular subjects or situations

    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
    only
    -0.71
    atre
    -0.68
    lied
    -0.67
    item
    -0.67
    toggle
    -0.67
    é¾
    -0.67
    lations
    -0.66
    advertising
    -0.66
    Runner
    -0.65
    lying
    -0.65
    POSITIVE LOGITS
     susceptible
    0.83
     considering
    0.80
     noticeable
    0.75
     geared
    0.73
     vulnerable
    0.72
     emphasized
    0.71
     suited
    0.71
     noteworthy
    0.70
     rewarding
    0.67
     appreciated
    0.67
    Activations Density 0.021%

    No Known Activations