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. 1-RES-JB
    6. 23427
    Prev
    Next
    INDEX
    Explanations

    intense or extreme descriptions or statements

    oai_token-act-pair · gpt-3.5-turbo

    the concept of "crazy" or extreme behavior and situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewed
    -0.98
    tein
    -0.87
    ribut
    -0.83
    ribute
    -0.83
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.78
     Cheong
    -0.78
    lain
    -0.70
    apers
    -0.69
    AUT
    -0.68
    arers
    -0.68
    POSITIVE LOGITS
     crazy
    0.89
     nuts
    0.82
     insane
    0.74
     chic
    0.72
     overboard
    0.71
     insanity
    0.69
    crazy
    0.69
     darling
    0.69
     beasts
    0.69
    ishly
    0.67
    Activations Density 0.011%

    No Known Activations