© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1678
    Prev
    Next
    INDEX
    Explanations

    phrases indicating resolution values in the format of "number x number"

    oai_token-act-pair · gpt-3.5-turbo

    specific resolutions and dimensions related to screens or displays

    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
    kson
    -0.86
    sburgh
    -0.81
    rent
    -0.80
    ogy
    -0.77
     Seym
    -0.75
    aceous
    -0.73
    auna
    -0.72
    ties
    -0.71
    perty
    -0.70
    assetsadobe
    -0.70
    POSITIVE LOGITS
    LP
    0.85
    USB
    0.83
    wid
    0.76
    Glass
    0.74
    Liquid
    0.72
     magnification
    0.72
    LAB
    0.71
    Area
    0.71
    IU
    0.71
     USB
    0.70
    Activations Density 0.029%

    No Known Activations