© 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. 3146
    Prev
    Next
    INDEX
    Explanations

    photographs with credits at the end of articles

    oai_token-act-pair · gpt-3.5-turbo

    references to photographs or imagery in the document

    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
    entimes
    -0.81
    kees
    -0.78
     leveling
    -0.71
     adversaries
    -0.70
     leveled
    -0.68
     unsett
    -0.68
     debates
    -0.67
     topics
    -0.66
    ĪĴ
    -0.65
     sooner
    -0.65
    POSITIVE LOGITS
     Courtesy
    1.40
     Provided
    1.30
     Shutterstock
    1.29
     ©
    1.28
     Getty
    1.28
     REUTERS
    1.22
     Wikimedia
    1.16
     AFP
    1.14
     COURT
    1.08
     Flickr
    1.05
    Activations Density 0.028%

    No Known Activations