© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 9900
    Prev
    Next
    INDEX
    Explanations

    acronyms related to a specific scientific journal or publication

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the acronym "PLoS" in the context of scientific publications

    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
    ered
    -0.82
    rying
    -0.67
     Clicker
    -0.63
    ministic
    -0.62
     rhy
    -0.62
    erer
    -0.61
    OWS
    -0.60
     ext
    -0.59
    uated
    -0.58
     Turing
    -0.58
    POSITIVE LOGITS
    hiba
    1.17
    opher
    1.11
    sein
    1.03
    ullivan
    0.96
    metics
    0.96
    ophical
    0.96
    pite
    0.95
    omal
    0.94
    omething
    0.91
    hing
    0.89
    Activations Density 0.034%

    No Known Activations