© 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. 17668
    Prev
    Next
    INDEX
    Explanations

    actions or functionalities that allow users to interact with different software applications or technology

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate user actions and interactions within applications or platforms

    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
    inventoryQuantity
    -0.80
    quickShipAvailable
    -0.65
    paren
    -0.65
    é¾įå¥ij士
    -0.63
    catentry
    -0.61
    SourceFile
    -0.61
    Translation
    -0.60
     crises
    -0.60
    Politics
    -0.59
    Capital
    -0.58
    POSITIVE LOGITS
     beware
    0.98
    ggles
    0.94
     browse
    0.89
     download
    0.87
     choose
    0.87
     enjoy
    0.86
     customize
    0.86
     navigate
    0.85
     indulge
    0.85
     learn
    0.82
    Activations Density 0.307%

    No Known Activations