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. 5646
    Prev
    Next
    INDEX
    Explanations

    references to newsletters or emails from the New York Times

    oai_token-act-pair · gpt-3.5-turbo

    references to newsletters, specifically from the New York Times

    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
     mole
    -0.66
     reformed
    -0.66
    chance
    -0.64
    eur
    -0.61
    jury
    -0.61
     occasion
    -0.57
     Ic
    -0.57
    zh
    -0.56
    lig
    -0.56
    gged
    -0.56
    POSITIVE LOGITS
     newsletters
    0.80
     toggle
    0.80
    é¾įå¥ij士
    0.78
    azines
    0.77
    sylv
    0.74
    ļéĨĴ
    0.73
     cartoons
    0.72
     dilig
    0.71
    soever
    0.70
     Emails
    0.69
    Activations Density 0.013%

    No Known Activations