Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 5342
    Prev
    Next
    INDEX
    Explanations

    text related to purchasing or viewing photographs with an emphasis on legal mentions

    oai_token-act-pair · gpt-3.5-turbo

    references to photographs and images in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oplan
    -0.81
    warts
    -0.81
    nut
    -0.77
    icion
    -0.77
    dfx
    -0.76
    iqueness
    -0.74
    depend
    -0.73
    riched
    -0.73
    cius
    -0.72
    prime
    -0.72
    POSITIVE LOGITS
     IMAGES
    0.87
     Courtesy
    0.84
     PHOTO
    0.81
     Shelley
    0.78
     Expand
    0.78
    sburgh
    0.76
     Photographer
    0.76
     Photograph
    0.76
     caption
    0.75
     Painting
    0.74
    Activations Density 0.007%

    No Known Activations