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. 7-RES-JB
    6. 10612
    Prev
    Next
    INDEX
    Explanations

    news-related content verbs with a focus on reporting or analyzing information

    oai_token-act-pair · gpt-3.5-turbo

    attributions and references to sources or observations

    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
    rontal
    -0.70
    lux
    -0.69
    animate
    -0.66
    rang
    -0.66
     INCLUD
    -0.64
    emate
    -0.64
    relation
    -0.61
    anking
    -0.61
    chrome
    -0.60
    CLUD
    -0.60
    POSITIVE LOGITS
     aptly
    0.76
     eloqu
    0.76
     succinct
    0.70
     quoting
    0.69
     bluntly
    0.69
    terday
    0.67
     Sov
    0.67
     pointed
    0.66
     optim
    0.64
    ":[
    0.64
    Activations Density 0.093%

    No Known Activations