© 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. 6-RES-JB
    11. 17358
    Prev
    Next
    INDEX
    Explanations

    short phrases or sentences that are formatted as lists

    oai_token-act-pair · gpt-3.5-turbo

    references to list structures and organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     McAuliffe
    -0.72
     Samar
    -0.70
     carriage
    -0.67
     braking
    -0.66
    Benz
    -0.66
    inea
    -0.66
    coni
    -0.65
    iday
    -0.65
    steen
    -0.64
    ãĥ¡
    -0.64
    POSITIVE LOGITS
     Lists
    0.80
    DragonMagazine
    0.73
     aggregation
    0.73
     lists
    0.72
     curated
    0.71
     "$:/
    0.71
     shelves
    0.71
     widget
    0.71
    ilogy
    0.71
     charts
    0.70
    Activations Density 0.568%

    No Known Activations