© 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. 0-RES-JB
    11. 6795
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning or related to written publications like articles, books, and journals

    oai_token-act-pair · gpt-3.5-turbo

    references to articles and their frequency in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wait
    -0.69
    plex
    -0.68
    alth
    -0.67
     flanked
    -0.64
    ossession
    -0.63
    uph
    -0.62
    pped
    -0.60
     Minotaur
    -0.60
    ioch
    -0.60
    mpire
    -0.59
    POSITIVE LOGITS
     articles
    3.57
     Articles
    2.47
     article
    2.29
    articles
    2.20
     publications
    1.87
     essays
    1.76
    article
    1.71
     posts
    1.71
     Article
    1.63
    Article
    1.60
    Activations Density 0.017%

    No Known Activations