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

    Neuronpedia

    APICircuit 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. 10377
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal agreements or regulations

    oai_token-act-pair · gpt-3.5-turbo

    references to international agreements and policies

    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
     souven
    -0.71
     rehearsal
    -0.70
     prelim
    -0.68
     sibling
    -0.66
     resil
    -0.64
    ahime
    -0.64
    crew
    -0.64
     bung
    -0.64
     finalists
    -0.62
     exterior
    -0.61
    POSITIVE LOGITS
    Professor
    1.34
    SPONSORED
    1.28
    Writing
    1.17
    He
    1.15
    Prof
    1.11
     Professor
    1.03
    His
    1.02
    Indeed
    0.99
    Others
    0.95
     Chomsky
    0.94
    Activations Density 0.491%

    No Known Activations