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. 20545
    Prev
    Next
    INDEX
    Explanations

    disclaimers indicating that opinions expressed are the author's own and do not necessarily reflect those of an organization

    oai_token-act-pair · gpt-3.5-turbo

    statements regarding the ownership and representation of opinions in articles

    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
     Faster
    -0.76
    ciation
    -0.65
    saf
    -0.63
    delay
    -0.63
    requ
    -0.62
     brut
    -0.61
     Improved
    -0.60
     Reduced
    -0.60
     Gin
    -0.59
    case
    -0.59
    POSITIVE LOGITS
     editorial
    0.82
     opinions
    0.80
     endorsement
    0.71
    ãĥĦ
    0.65
     trademarks
    0.64
    EngineDebug
    0.63
     belong
    0.63
     affiliation
    0.63
    çīĪ
    0.63
    ravis
    0.63
    Activations Density 0.125%

    No Known Activations