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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12385
    Prev
    Next
    INDEX
    Explanations

    dates, technical terms, and separators in a structured format

    oai_token-act-pair · gpt-3.5-turbo

    references to dates and articles

    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
     halting
    -0.87
     altru
    -0.79
     forcibly
    -0.77
     ostensibly
    -0.76
     provocation
    -0.76
     paradox
    -0.76
     fort
    -0.75
     theoretically
    -0.74
     conscientious
    -0.74
     unb
    -0.73
    POSITIVE LOGITS
     Browse
    1.47
     Reviews
    1.45
     Articles
    1.39
     Videos
    1.34
     Downloads
    1.34
     Links
    1.31
    Pages
    1.31
     Tags
    1.30
     Contents
    1.30
     Search
    1.30
    Activations Density 0.312%

    No Known Activations