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. 10-RES-JB
    6. 17993
    Prev
    Next
    INDEX
    Explanations

    terms related to various real-world events, such as Bitcoin Expo, Iran nuclear bill, and Jared Lee Loughner

    oai_token-act-pair · gpt-3.5-turbo

    references to events or discussions related to Bitcoin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Azerb
    -0.55
    anwhile
    -0.54
     Beir
    -0.51
    etheless
    -0.51
     Flavoring
    -0.50
    oÄŁ
    -0.50
     elsewhere
    -0.49
     adjoining
    -0.48
     wiser
    -0.48
     Presbyter
    -0.48
    POSITIVE LOGITS
    database
    0.44
     web
    0.44
     body
    0.44
      
    0.43
     ðŁ
    0.42
    utterstock
    0.42
     internet
    0.41
     birth
    0.41
    gorithm
    0.40
     meme
    0.40
    Activations Density 1.329%

    No Known Activations