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. 20113
    Prev
    Next
    INDEX
    Explanations

    words in a different character encoding format

    oai_token-act-pair · gpt-3.5-turbo

    scss loving or preferring pleasant sensory experiences

    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
     assignment
    -0.79
     legally
    -0.77
     unidentified
    -0.73
     lawfully
    -0.73
     bloc
    -0.72
     intended
    -0.71
     divest
    -0.71
     probation
    -0.71
     constitutionally
    -0.70
     deceived
    -0.69
    POSITIVE LOGITS
    Anyway
    1.15
    Advertisement
    1.15
    Conclusion
    1.03
    Luckily
    0.99
    Below
    0.98
    Thankfully
    0.98
    CONCLUS
    0.98
    Advertisements
    0.97
    Appearance
    0.97
    Favorite
    0.97
    Activations Density 0.536%

    No Known Activations