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

    Neuronpedia

    Jacobian LensNEW
    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. 8533
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical or medical conditions rated with high importance

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific concept or term repeatedly throughout the text

    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
    é¾
    -0.83
     GOODMAN
    -0.63
    perse
    -0.62
    OME
    -0.60
     swirling
    -0.59
     SetTextColor
    -0.59
    burst
    -0.59
    ainers
    -0.59
     nets
    -0.58
    izoph
    -0.58
    POSITIVE LOGITS
    ller
    1.03
    cific
    1.02
    anut
    0.99
    oples
    0.96
    rer
    0.94
    cies
    0.93
    asant
    0.92
    cial
    0.91
    llers
    0.89
    eps
    0.86
    Activations Density 0.013%

    No Known Activations