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. 19824
    Prev
    Next
    INDEX
    Explanations

    page numbers and citation information in a document

    oai_token-act-pair · gpt-3.5-turbo

    references to specific publications or citations

    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
    ndra
    -0.72
     Clicker
    -0.68
     Tribunal
    -0.58
     zone
    -0.57
     winner
    -0.57
    proof
    -0.56
     overnight
    -0.56
     Chow
    -0.55
     awoke
    -0.54
     imperson
    -0.54
    POSITIVE LOGITS
     seq
    1.00
     384
    0.89
     324
    0.89
     409
    0.88
     334
    0.88
     348
    0.86
     313
    0.85
     388
    0.85
     387
    0.85
     326
    0.85
    Activations Density 0.058%

    No Known Activations