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

    Neuronpedia

    Jacobian LensNEW
    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. 1884
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to various fields like technology, medicine, and gaming

    oai_token-act-pair · gpt-3.5-turbo

    prominent nouns and technical terms related to various subjects

    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
    utics
    -0.69
    ertodd
    -0.62
    terday
    -0.61
    paces
    -0.58
    ashington
    -0.57
    DonaldTrump
    -0.57
     Rica
    -0.56
    abwe
    -0.55
    ģĸ
    -0.55
    each
    -0.54
    POSITIVE LOGITS
     aspect
    0.93
     portion
    0.89
    iest
    0.86
     version
    0.83
    liest
    0.81
     side
    0.80
     analogy
    0.77
     assumption
    0.75
     hypothesis
    0.75
     equivalent
    0.73
    Activations Density 0.938%

    No Known Activations