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. 8-RES-JB
    6. 15906
    Prev
    Next
    INDEX
    Explanations

    references to specific organizations or entities within a larger context

    oai_token-act-pair · gpt-3.5-turbo

    references to notable individuals or historical figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shutterstock
    -0.44
     metaphors
    -0.37
     restrooms
    -0.36
     sidewalks
    -0.36
     whales
    -0.35
     hurricanes
    -0.34
     gallon
    -0.34
     noun
    -0.33
     latitude
    -0.33
     analogy
    -0.33
    POSITIVE LOGITS
     sugg
    0.45
     embr
    0.41
     accomp
    0.40
    ´
    0.38
    urther
    0.38
    Reloaded
    0.38
    º
    0.37
    ®
    0.37
     cryst
    0.37
    ī
    0.36
    Activations Density 3.050%

    No Known Activations