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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 2738
    Prev
    Next
    INDEX
    Explanations

    photographs and related captions

    oai_token-act-pair · gpt-3.5-turbo

    references to photographs or images

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uckle
    -0.80
    powers
    -0.77
    ims
    -0.76
    astically
    -0.73
    resses
    -0.70
    ortun
    -0.70
    uchs
    -0.69
    iling
    -0.69
    oler
    -0.69
    izen
    -0.69
    POSITIVE LOGITS
     Photo
    1.04
    Photo
    1.02
     Album
    0.94
     Photographer
    0.93
     Thumbnails
    0.92
    journal
    0.90
     Photograph
    0.88
    photo
    0.87
     Courtesy
    0.86
     Gallery
    0.85
    Activations Density 0.017%

    No Known Activations