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. 8630
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names

    oai_token-act-pair · gpt-3.5-turbo

    phrases or sentences that contain humor or comedic elements

    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
    £ı
    -0.75
    exempt
    -0.72
    wcs
    -0.72
     equival
    -0.70
     exempted
    -0.69
    Government
    -0.67
    vernment
    -0.67
    ItemTracker
    -0.66
     operational
    -0.64
     substantially
    -0.62
    POSITIVE LOGITS
     Chloe
    1.10
     Kristen
    1.08
     Ginny
    1.08
     Lauren
    1.07
     Jess
    1.06
     Jessica
    1.04
     Nicole
    1.04
     Joey
    1.03
     Jenna
    1.03
     Vanessa
    1.03
    Activations Density 0.680%

    No Known Activations