© 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. 14466
    Prev
    Next
    INDEX
    Explanations

    numerical values such as measurements and quantities

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and measurements

    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
     "$:/
    -0.72
    auder
    -0.68
    assic
    -0.64
    anan
    -0.63
    ouver
    -0.62
    inois
    -0.62
    gypt
    -0.61
     struggle
    -0.59
    achus
    -0.59
     Humph
    -0.59
    POSITIVE LOGITS
    dden
    0.79
    200000
    0.71
    ffff
    0.66
    pixel
    0.66
    cycles
    0.62
    FFFF
    0.62
    000000
    0.61
    VALUE
    0.61
     HRC
    0.61
    rocket
    0.61
    Activations Density 0.091%

    No Known Activations