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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 19361
    Prev
    Next
    INDEX
    Explanations

    instances where the word "Sun" is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    references to news sources and specific journalism terms

    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
     Marketable
    -0.75
    ãĥĥãĥī
    -0.71
    wordpress
    -0.65
    >>\
    -0.64
    ername
    -0.63
    imens
    -0.62
    */(
    -0.62
    shown
    -0.61
    ãĤ¤ãĥĪ
    -0.61
    POST
    -0.61
    POSITIVE LOGITS
    opol
    0.80
    BuyableInstoreAndOnline
    0.70
     Night
    0.70
    onday
    0.70
     Morning
    0.68
     Shutterstock
    0.68
     Moon
    0.67
     Shattered
    0.67
    din
    0.66
     nights
    0.65
    Activations Density 0.195%

    No Known Activations