© 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. 8-RES-JB
    11. 1226
    Prev
    Next
    INDEX
    Explanations

    the word "pixel" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms specifically related to pixels in digital design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kson
    -0.76
    OME
    -0.71
    doms
    -0.70
    ocrates
    -0.70
    UNE
    -0.67
    shore
    -0.66
    ãĤ·ãĥ£
    -0.66
     Fargo
    -0.66
    é¾įå
    -0.65
    jri
    -0.65
    POSITIVE LOGITS
    ated
    0.96
     shader
    0.87
    agraph
    0.80
    igans
    0.75
    ixels
    0.74
    RGB
    0.73
    perfect
    0.73
    ounce
    0.72
    rendered
    0.72
    izer
    0.70
    Activations Density 0.031%

    No Known Activations