© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14473
    Prev
    Next
    INDEX
    Explanations

    instances where individuals express strong emotional sentiments toward a particular subject

    oai_token-act-pair · gpt-3.5-turbo

    expressions of desire and concern from a collective perspective

    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
     Miracle
    -0.67
    ãĥĺ
    -0.65
     Restoration
    -0.65
    Delivery
    -0.65
     succession
    -0.63
    stuff
    -0.62
    fficiency
    -0.62
     Illum
    -0.61
     Escape
    -0.60
     disappearing
    -0.60
    POSITIVE LOGITS
     worries
    1.24
     want
    1.17
     fears
    1.17
     worry
    1.16
     worried
    1.14
     thinks
    1.13
     think
    1.11
     urge
    1.10
     resent
    1.10
     wish
    1.09
    Activations Density 0.601%

    No Known Activations