© 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. 0-RES-JB
    11. 15415
    Prev
    Next
    INDEX
    Explanations

    praise or admiration for someone or something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "praised" or similar terms indicating commendation

    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
     exit
    -0.66
    seed
    -0.66
     proxy
    -0.62
    exit
    -0.61
     insur
    -0.60
     sequence
    -0.59
     Entry
    -0.58
     denomin
    -0.58
     probability
    -0.57
    abs
    -0.57
    POSITIVE LOGITS
     praised
    3.27
     lauded
    2.63
     applauded
    2.50
     hailed
    2.15
     thanked
    2.13
     congratulated
    2.08
     praising
    2.01
     criticized
    1.96
     praises
    1.94
     criticised
    1.92
    Activations Density 0.017%

    No Known Activations