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. 1-RES-JB
    6. 11070
    Prev
    Next
    INDEX
    Explanations

    references to the image hosting platform Flickr

    oai_token-act-pair · gpt-3.5-turbo

    references to the image-sharing platform Flickr

    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
    stals
    -0.77
    gran
    -0.76
     loud
    -0.67
     accur
    -0.66
    xon
    -0.66
    eering
    -0.66
    ordial
    -0.65
     ages
    -0.62
    aneously
    -0.61
    stal
    -0.61
    POSITIVE LOGITS
    Flickr
    1.51
     Flickr
    1.38
     Shutterstock
    1.05
     Wikimedia
    1.04
    ickr
    1.03
    utterstock
    0.97
    Library
    0.96
    photo
    0.91
     Photo
    0.89
     Photographer
    0.88
    Activations Density 0.005%

    No Known Activations