© 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. 0-RES-JB
    11. 2228
    Prev
    Next
    INDEX
    Explanations

    materials or items that are resistant to damage or wear

    oai_token-act-pair · gpt-3.5-turbo

    terms related to resistance in various contexts

    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
    oga
    -0.75
    nings
    -0.72
     hust
    -0.71
    atre
    -0.70
     Kuala
    -0.67
    AGES
    -0.66
    ¥µ
    -0.64
    tesy
    -0.64
     Gos
    -0.64
    acht
    -0.62
    POSITIVE LOGITS
     resistant
    3.57
    resistant
    3.38
     resistance
    1.89
     resilient
    1.85
     tolerant
    1.66
     susceptible
    1.51
     Resistance
    1.44
     resists
    1.35
     suscept
    1.32
     resist
    1.30
    Activations Density 0.018%

    No Known Activations