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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 2249
    Prev
    Next
    INDEX
    Explanations

    references to a specific name "Mack"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Mack" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾įå¥ij士
    -0.77
    é»Ĵ
    -0.73
    âĸ¬
    -0.70
     revolving
    -0.67
     checkout
    -0.67
    ++++++++
    -0.66
    ORED
    -0.65
    =-=-=-=-=-=-=-=-
    -0.63
    otypes
    -0.61
     eclipse
    -0.61
    POSITIVE LOGITS
    enzie
    1.69
    intosh
    1.55
    innon
    1.17
    eting
    0.98
    hews
    0.97
    luster
    0.96
    minster
    0.94
    ham
    0.93
    downs
    0.92
    ling
    0.91
    Activations Density 0.033%

    No Known Activations