© 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. 10-RES-JB
    11. 11528
    Prev
    Next
    INDEX
    Explanations

    keywords related to computer programming, specifically focusing on data structures and syntax

    oai_token-act-pair · gpt-3.5-turbo

    elements related to programming and technical configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atoon
    -0.89
    anga
    -0.73
    atur
    -0.71
     Huss
    -0.70
    idae
    -0.70
    ageddon
    -0.69
    antz
    -0.68
    uminum
    -0.68
    iary
    -0.67
     Aviv
    -0.67
    POSITIVE LOGITS
    NAME
    1.70
    DIR
    1.70
    USER
    1.68
    SIZE
    1.67
    DATA
    1.65
    LOAD
    1.64
    PATH
    1.62
    FILE
    1.62
    WARE
    1.62
    OUT
    1.56
    Activations Density 0.075%

    No Known Activations