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. 11-RES-JB
    6. 18130
    Prev
    Next
    INDEX
    Explanations

    words related to photography and camera equipment

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to photographic equipment and techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nug
    -0.83
     Pledge
    -0.79
    soType
    -0.78
     Vendor
    -0.75
     Contribut
    -0.69
    Lua
    -0.68
    forge
    -0.68
    iliated
    -0.67
    Slot
    -0.66
    ibus
    -0.66
    POSITIVE LOGITS
     selfies
    1.42
     portraits
    1.33
     photographs
    1.32
     photos
    1.28
     shots
    1.28
     footage
    1.27
     photography
    1.27
     JPEG
    1.24
     images
    1.22
     HDR
    1.21
    Activations Density 0.358%

    No Known Activations