© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 2739
    Prev
    Next
    INDEX
    Explanations

    technology-related terms or organizations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various media and technology companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.66
     sled
    -0.64
     gar
    -0.63
     pand
    -0.62
     gorilla
    -0.62
     supervised
    -0.62
     reintrodu
    -0.61
     visitation
    -0.61
     settlements
    -0.61
     colors
    -0.61
    POSITIVE LOGITS
    Daily
    1.27
    News
    1.17
    Blog
    1.11
    Politics
    1.09
     Magazine
    1.09
     Daily
    1.09
    daily
    1.08
    aretz
    1.05
     Weekly
    1.02
    Week
    1.02
    Activations Density 0.247%

    No Known Activations