© 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. 7-RES-JB
    11. 14233
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of belittling or ridiculing

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "belittle" and related terms expressing diminishment or belittlement

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    inals
    -0.99
    inal
    -0.93
    anmar
    -0.91
    imus
    -0.87
    itives
    -0.85
    ropri
    -0.82
    iating
    -0.80
    ing
    -0.78
    yrus
    -0.77
    ees
    -0.76
    POSITIVE LOGITS
    cknowled
    0.76
     Chak
    0.70
     Hook
    0.67
    obyl
    0.67
     Conrad
    0.66
     fracture
    0.66
     Brav
    0.65
    ^^^^
    0.64
    ervative
    0.64
    fish
    0.64
    Activations Density 0.079%

    No Known Activations