© 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. 3384
    Prev
    Next
    INDEX
    Explanations

    information related to creating correct image shadows, highlights, reflections, and contrasts

    oai_token-act-pair · gpt-3.5-turbo

    elements related to visual and technical aspects of image creation

    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
     Nug
    -0.87
    leaders
    -0.70
     vending
    -0.70
     playbook
    -0.70
    ezvous
    -0.70
     Burger
    -0.69
    NAS
    -0.68
    edience
    -0.68
    ixir
    -0.67
     Travis
    -0.67
    POSITIVE LOGITS
     pixels
    1.45
     pixel
    1.40
     ali
    1.37
     shadows
    1.36
     blur
    1.34
     blurry
    1.33
     blurred
    1.31
     shading
    1.31
     saturation
    1.28
     JPEG
    1.24
    Activations Density 0.462%

    No Known Activations