© 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. 0-RES-JB
    11. 10941
    Prev
    Next
    INDEX
    Explanations

    photographs or images

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Photos."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     continu
    -0.72
     pipe
    -0.70
     tract
    -0.69
     undert
    -0.69
     incre
    -0.66
     tobacco
    -0.65
     grant
    -0.65
     downt
    -0.64
     deviation
    -0.64
     weaker
    -0.64
    POSITIVE LOGITS
     Photos
    4.07
    Photos
    2.44
     photos
    2.20
    photos
    2.09
     Photo
    1.92
    Phot
    1.86
     Images
    1.85
     Photography
    1.77
     Pictures
    1.75
     Photograph
    1.75
    Activations Density 0.010%

    No Known Activations