© 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. 2-RES-JB
    11. 14762
    Prev
    Next
    INDEX
    Explanations

    the word 'orders'

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "orders."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Miliband
    -0.71
     Volks
    -0.70
     Berlin
    -0.69
    vae
    -0.69
     Libre
    -0.68
     Raleigh
    -0.68
    Gordon
    -0.66
     Volkswagen
    -0.65
    ylene
    -0.65
     Rodham
    -0.65
    POSITIVE LOGITS
     orders
    1.23
    etary
    0.98
    hops
    0.90
    avorite
    0.89
    pread
    0.86
     ordering
    0.85
     Orders
    0.85
     ordered
    0.79
     prescribe
    0.79
    ylum
    0.78
    Activations Density 0.009%

    No Known Activations