© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 292
    Prev
    Next
    INDEX
    Explanations

    mentions of photographs or images

    oai_token-act-pair · gpt-3.5-turbo

    references to images or photos

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    okin
    -0.76
    warts
    -0.73
    oplan
    -0.72
    iqueness
    -0.71
    omsky
    -0.69
    icion
    -0.68
    ollo
    -0.68
    fing
    -0.68
    worldly
    -0.68
    urg
    -0.67
    POSITIVE LOGITS
     Courtesy
    0.82
     Photograph
    0.73
     IMAGES
    0.71
    SHARE
    0.71
     Fraz
    0.71
     Painting
    0.71
     Flood
    0.71
     caption
    0.71
     Mellon
    0.69
    Madison
    0.68
    Activations Density 0.006%

    No Known Activations