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. 19514
    Prev
    Next
    INDEX
    Explanations

    companies and organizations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate leadership or prominence in various industries or sectors

    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
    ieties
    -0.91
    ppings
    -0.88
    SPONSORED
    -0.82
    ieu
    -0.80
    UTERS
    -0.77
    another
    -0.77
    later
    -0.77
    maybe
    -0.76
    things
    -0.76
    might
    -0.75
    POSITIVE LOGITS
     Licensed
    1.01
     immersive
    0.95
     Certified
    0.95
     interactive
    0.94
     curated
    0.93
     comprehensive
    0.93
     FREE
    0.91
     award
    0.88
     premium
    0.87
     professional
    0.87
    Activations Density 0.366%

    No Known Activations