© 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. 9-RES-JB
    11. 15721
    Prev
    Next
    INDEX
    Explanations

    visual descriptions conveying information

    oai_token-act-pair · gpt-3.5-turbo

    instances of observation or seeing in contexts that involve images or photographs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nih
    -0.72
    phrine
    -0.71
    aceutical
    -0.70
     preached
    -0.64
     coined
    -0.64
    icide
    -0.63
    ospital
    -0.62
     supernatural
    -0.61
    utenberg
    -0.59
    ricular
    -0.59
    POSITIVE LOGITS
     screenshot
    1.34
     screenshots
    1.26
     below
    1.25
     pics
    1.17
     gallery
    1.14
     illustration
    1.14
     pictures
    1.13
    below
    1.11
     photos
    1.10
     diagram
    1.09
    Activations Density 0.227%

    No Known Activations