© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3399
    Prev
    Next
    INDEX
    Explanations

    references to news articles accompanied by images

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    mentions of the "Getty" brand or images from Getty Images

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     creek
    -0.65
     mistake
    -0.61
    kered
    -0.60
     bru
    -0.60
     infiltr
    -0.60
     unch
    -0.60
     privilege
    -0.60
     brill
    -0.60
     trooper
    -0.60
     sadd
    -0.57
    POSITIVE LOGITS
     Images
    1.93
    sburg
    1.57
    Images
    1.52
    images
    1.02
    sburgh
    0.96
     Features
    0.93
    Photos
    0.90
     IMAGES
    0.90
     Photos
    0.89
     Image
    0.88
    Activations Density 0.015%

    No Known Activations