© 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. 10-RES-JB
    11. 5925
    Prev
    Next
    INDEX
    Explanations

    time-related words and expressions

    oai_token-act-pair · gpt-3.5-turbo

    references to personal growth and reflection over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ãĥ¼ãĥĨãĤ£
    -0.78
     Yesterday
    -0.71
    photos
    -0.67
    MD
    -0.65
    Yesterday
    -0.62
     Tomorrow
    -0.62
     yesterday
    -0.62
     tomorrow
    -0.61
    worst
    -0.60
     Tray
    -0.60
    POSITIVE LOGITS
     became
    1.29
     realized
    1.24
     become
    1.23
     realised
    1.20
     becomes
    1.17
     gradually
    1.12
     morphed
    1.10
     began
    1.08
     realize
    1.06
    bec
    1.05
    Activations Density 0.417%

    No Known Activations