© 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. 1-RES-JB
    11. 3773
    Prev
    Next
    INDEX
    Explanations

    references to and mentions of photographs

    oai_token-act-pair · gpt-3.5-turbo

    mentions of photographs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lde
    -0.73
    osi
    -0.72
    demand
    -0.67
    rel
    -0.66
    aples
    -0.65
    charge
    -0.65
    upuncture
    -0.64
    ressive
    -0.64
    fy
    -0.63
    end
    -0.63
    POSITIVE LOGITS
     photographs
    1.38
     photographed
    1.24
    ynthesis
    1.20
    ographs
    1.12
     Photograph
    1.09
     photography
    1.09
     Photographer
    1.08
     photographers
    1.07
     PHOTO
    1.03
    photos
    1.03
    Activations Density 0.013%

    No Known Activations