© 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. 8-RES-JB
    11. 11254
    Prev
    Next
    INDEX
    Explanations

    words related to emotions, specifically anger and uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    terms and concepts associated with emotions and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    versions
    -0.75
    miss
    -0.69
    âĹ¼
    -0.66
    ¯
    -0.64
     counterparts
    -0.63
     psychiat
    -0.61
    ECD
    -0.57
    SAN
    -0.56
    authent
    -0.56
     ancest
    -0.56
    POSITIVE LOGITS
     Matters
    1.02
     Comes
    1.01
     Begins
    1.01
    ful
    0.98
     Required
    0.93
     Facts
    0.90
     Lessons
    0.90
    FUL
    0.90
     Problems
    0.89
    fully
    0.88
    Activations Density 0.278%

    No Known Activations