© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    6. 6291
    Prev
    Next
    INDEX
    Explanations

    phrases related to news articles with photo credits

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Photo" indicating visual content or imagery

    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
     sett
    -0.72
     empires
    -0.71
     incre
    -0.68
     gods
    -0.68
    ellig
    -0.67
    une
    -0.66
     desp
    -0.66
    enum
    -0.64
    ãĤ¡
    -0.64
     dwarves
    -0.64
    POSITIVE LOGITS
     Photo
    3.90
    Photo
    2.35
     PHOTO
    2.32
    photo
    2.32
     Photos
    2.13
     photo
    2.12
     Photograph
    1.94
     Picture
    1.93
     Photographer
    1.85
    photos
    1.76
    Activations Density 0.011%

    No Known Activations