Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 9657
    Prev
    Next
    INDEX
    Explanations

    instances of unused formatting characters such as 'Ċ'

    oai_token-act-pair · gpt-3.5-turbo

    instances of strong emotions or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     torpedo
    -1.05
     mushroom
    -1.04
     metic
    -0.93
     trave
    -0.90
     iron
    -0.88
     moss
    -0.86
     gelatin
    -0.86
     rubber
    -0.85
     discern
    -0.85
     fuse
    -0.85
    POSITIVE LOGITS
    âĢ
    2.25
    ADVERTISEMENT
    1.45
    Asked
    1.45
    âĸł
    1.43
    Translation
    1.41
    Others
    1.37
    âľ
    1.37
    Regardless
    1.35
    Walker
    1.35
    âĸº
    1.35
    Activations Density 0.219%

    No Known Activations