© 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. 11-RES-JB
    11. 20922
    Prev
    Next
    INDEX
    Explanations

    phrases related to images and their captions

    oai_token-act-pair · gpt-3.5-turbo

    references to images and their captions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    body
    -0.68
    DERR
    -0.65
    pole
    -0.62
    Condition
    -0.60
    Shape
    -0.59
    Advertisements
    -0.58
    ificant
    -0.58
    iqueness
    -0.58
    âĢİ
    -0.57
     prophe
    -0.57
    POSITIVE LOGITS
     toggle
    1.53
     Courtesy
    1.01
     REUTERS
    0.85
     FILE
    0.80
     screenshot
    0.74
     Image
    0.73
     Mehran
    0.71
     Chip
    0.70
     AFP
    0.70
     shutter
    0.69
    Activations Density 0.016%

    No Known Activations