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. 8-RES-JB
    6. 21529
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and infrastructure

    oai_token-act-pair · gpt-3.5-turbo

    references to technology and its applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Conclusion
    -0.70
    dor
    -0.69
    iversary
    -0.69
    deen
    -0.69
    wic
    -0.68
    ãģ®å®
    -0.68
    hus
    -0.67
    ovember
    -0.65
     Events
    -0.64
    soType
    -0.63
    POSITIVE LOGITS
     capabilities
    1.14
     technologies
    1.05
     patented
    1.04
     capable
    1.04
     powering
    1.03
     gadgets
    1.02
     capability
    1.01
     malfunction
    0.99
     automate
    0.98
     technology
    0.97
    Activations Density 0.758%

    No Known Activations