© 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. 9-RES-JB
    11. 2335
    Prev
    Next
    INDEX
    Explanations

    the word "is" followed by certain contextual elements

    oai_token-act-pair · gpt-3.5-turbo

    statements asserting a truth or fact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    throp
    -0.75
    rador
    -0.72
    andise
    -0.71
    sg
    -0.67
    asts
    -0.66
    stad
    -0.65
    appropriately
    -0.62
    ypes
    -0.62
    aded
    -0.62
    inventoryQuantity
    -0.60
    POSITIVE LOGITS
     nobody
    0.83
     none
    0.83
     that
    0.76
     nothing
    0.75
     neither
    0.74
     undeniable
    0.71
     nowhere
    0.69
     THAT
    0.67
     hardly
    0.66
    adays
    0.66
    Activations Density 0.061%

    No Known Activations