© 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. 6-RES-JB
    11. 17684
    Prev
    Next
    INDEX
    Explanations

    instances of the word "bullying."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "bully" and its variations, focusing on themes of bullying in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cise
    -0.75
    ateur
    -0.75
    aeda
    -0.73
     Donation
    -0.73
    cession
    -0.72
    ournal
    -0.72
    icrobial
    -0.71
    uncture
    -0.70
    uve
    -0.69
    arbon
    -0.69
    POSITIVE LOGITS
     bullies
    1.13
     bullying
    0.99
     bullied
    0.93
     bully
    0.93
     pul
    0.86
     behav
    0.85
    ãħĭ
    0.80
    iors
    0.72
    kids
    0.71
    girls
    0.68
    Activations Density 0.014%

    No Known Activations