© 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. 14340
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticizing others for their actions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating criticism or opposition

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    OTAL
    -0.77
    atl
    -0.76
    ieth
    -0.75
     awaits
    -0.74
    wang
    -0.71
    Gi
    -0.70
    ern
    -0.69
    edin
    -0.68
    orth
    -0.67
    adj
    -0.67
    POSITIVE LOGITS
     failing
    1.03
     daring
    0.96
     abandoning
    0.95
     allowing
    0.95
     having
    0.94
     being
    0.92
     inaction
    0.89
     refusing
    0.89
     violating
    0.86
     creating
    0.86
    Activations Density 0.098%

    No Known Activations