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

    Neuronpedia

    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. 10-RES-JB
    11. 12051
    Prev
    Next
    INDEX
    Explanations

    mentions or references to "USA TODAY"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Salman
    -0.71
    byn
    -0.69
     generations
    -0.68
     Kissinger
    -0.66
     haunt
    -0.64
    gone
    -0.64
     haun
    -0.62
    cles
    -0.62
    iHUD
    -0.61
    Introduced
    -0.61
    POSITIVE LOGITS
     NETWORK
    1.39
     Sports
    1.16
     SPORTS
    1.13
     Network
    0.90
    Sports
    0.84
    Money
    0.82
     Sport
    0.82
     Magazine
    0.80
    EW
    0.78
    Network
    0.77
    Activations Density 0.027%

    No Known Activations