Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-RES-JB
    6. 19048
    Prev
    Next
    INDEX
    Explanations

    proper nouns or acronyms with the word "AT" followed by a high activation score

    oai_token-act-pair · gpt-3.5-turbo

    the abbreviation "AT" and its various mentions throughout the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tsukuyomi
    -0.70
    perse
    -0.70
     Micha
    -0.66
    produ
    -0.66
    ingen
    -0.63
    dale
    -0.62
    Blade
    -0.60
    ãĥĭ
    -0.60
    place
    -0.59
     Ug
    -0.59
    POSITIVE LOGITS
    ICAN
    1.20
    RON
    0.99
    itudes
    0.95
    ECH
    0.95
    RIC
    0.94
    TAIN
    0.93
    oday
    0.93
    ainment
    0.92
    htaking
    0.91
    hetically
    0.90
    Activations Density 0.007%

    No Known Activations