© 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. 9-RES-JB
    11. 24285
    Prev
    Next
    INDEX
    Explanations

    words related to judgment or opinion, often expressing a strong viewpoint

    oai_token-act-pair · gpt-3.5-turbo

    emphasis on a specific topic, likely related to strong negative opinions or criticisms

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     ABE
    -0.73
     Doodle
    -0.65
     Ascension
    -0.63
     Shelter
    -0.62
     Tasman
    -0.61
    ilers
    -0.60
     RAD
    -0.60
    iewicz
    -0.60
     Wad
    -0.59
     Mirage
    -0.59
    POSITIVE LOGITS
    IJ
    1.20
    ª
    1.18
    «
    1.16
    appropriately
    1.09
    Ĵ
    1.07
    ij
    1.07
    ł
    1.04
    Ķ
    1.03
    almost
    1.03
    ¹
    1.01
    Activations Density 0.122%

    No Known Activations