© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 9937
    Prev
    Next
    INDEX
    Explanations

    the phrase "top stories you need to know."

    oai_token-act-pair · gpt-3.5-turbo

    references to top news stories and rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    naire
    -0.68
    ably
    -0.60
     Seym
    -0.60
    istically
    -0.59
    chard
    -0.59
    phia
    -0.58
    isse
    -0.56
    nces
    -0.56
    abiding
    -0.55
    ilipp
    -0.55
    POSITIVE LOGITS
     stories
    0.76
     celeb
    0.75
     headlines
    0.71
     trending
    0.64
    advertisement
    0.63
    ingen
    0.60
     articles
    0.60
     quotes
    0.59
    ICS
    0.59
     Stories
    0.58
    Activations Density 0.049%

    No Known Activations