© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 21098
    Prev
    Next
    INDEX
    Explanations

    proper nouns, likely related to images in a photo or article

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Photo."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omsky
    -0.82
    onson
    -0.75
    astically
    -0.73
    urious
    -0.73
    intern
    -0.73
    urg
    -0.72
    urnal
    -0.71
    iling
    -0.70
    ruce
    -0.70
    gen
    -0.70
    POSITIVE LOGITS
     Treasurer
    0.82
     IMAGES
    0.80
     Thumbnails
    0.78
     Courtesy
    0.78
     COUNTY
    0.77
     Annotations
    0.77
     toggle
    0.76
     Photo
    0.76
     Clerk
    0.76
    CLOSE
    0.75
    Activations Density 0.012%

    No Known Activations