© 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. 4-RES-JB
    11. 17156
    Prev
    Next
    INDEX
    Explanations

    names of global events and institutions

    oai_token-act-pair · gpt-3.5-turbo

    major global events and institutions, particularly in sports and health

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

    No Comments

    Negative Logits
    emia
    -0.73
    edge
    -0.65
    edy
    -0.65
    etsy
    -0.65
    dll
    -0.64
    intel
    -0.64
    else
    -0.60
     balcon
    -0.60
    oeuv
    -0.60
    olar
    -0.60
    POSITIVE LOGITS
    bernatorial
    0.94
     onwards
    0.68
    ategory
    0.67
    isode
    0.61
    cember
    0.59
     partName
    0.59
    ãĥ¼ãĤ¯
    0.59
     census
    0.59
     maiden
    0.59
     calendar
    0.59
    Activations Density 0.332%

    No Known Activations