© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 21002
    Prev
    Next
    INDEX
    Explanations

    details about event tickets

    oai_token-act-pair · gpt-3.5-turbo

    information related to ticket sales and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    warts
    -0.87
    Correct
    -0.81
    Output
    -0.68
    acters
    -0.66
    ths
    -0.64
    Flickr
    -0.63
    Translation
    -0.63
     Lomb
    -0.62
     blender
    -0.62
    output
    -0.61
    POSITIVE LOGITS
     priced
    1.04
    sale
    1.01
     Tickets
    0.95
     Ticket
    0.90
    Tickets
    0.90
     SOLD
    0.87
     tickets
    0.85
     ¥
    0.83
    sold
    0.82
    Price
    0.82
    Activations Density 0.084%

    No Known Activations