© 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. 0-RES-JB
    11. 2044
    Prev
    Next
    INDEX
    Explanations

    words related to breathing difficulties or respiratory issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to allergic reactions and wheezing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thor
    -0.68
     leap
    -0.61
     rooting
    -0.59
     Barrier
    -0.58
     Rugby
    -0.58
     transformation
    -0.57
     deficit
    -0.57
     classification
    -0.57
     silver
    -0.57
     IT
    -0.57
    POSITIVE LOGITS
    ez
    4.69
    eez
    1.45
    lez
    1.36
    eh
    1.35
    ev
    1.23
    ees
    1.22
    oz
    1.20
    ezvous
    1.19
    zeb
    1.18
    eb
    1.16
    Activations Density 0.016%

    No Known Activations