© 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 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. 8-RES-JB
    11. 20028
    Prev
    Next
    INDEX
    Explanations

    phrases indicating extreme judgment or evaluation, especially negative ones

    oai_token-act-pair · gpt-3.5-turbo

    intensive expressions of negativity or criticism

    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
    ////
    -0.74
    actionDate
    -0.71
    anners
    -0.70
    */(
    -0.70
     Springs
    -0.69
    OHN
    -0.67
    maid
    -0.67
    pell
    -0.66
     Tik
    -0.65
    ktop
    -0.65
    POSITIVE LOGITS
     disregard
    1.09
     strangers
    1.04
     annihilation
    1.03
     domination
    0.97
     fabrication
    0.94
     destruction
    0.92
     devastation
    0.92
    itarian
    0.91
     darkness
    0.90
    itar
    0.89
    Activations Density 0.073%

    No Known Activations