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. 0-RES-JB
    6. 17548
    Prev
    Next
    INDEX
    Explanations

    references to image copyrights

    oai_token-act-pair · gpt-3.5-turbo

    references to images in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prep
    -0.71
     roommate
    -0.69
     certified
    -0.68
     ass
    -0.68
     ages
    -0.67
     ear
    -0.67
     duty
    -0.65
    oped
    -0.64
     du
    -0.63
     viol
    -0.63
    POSITIVE LOGITS
    Image
    4.09
    Images
    2.26
     Image
    2.21
    image
    2.06
    Photo
    1.93
    Media
    1.87
    Picture
    1.57
     image
    1.47
     Images
    1.46
    images
    1.38
    Activations Density 0.019%

    No Known Activations