© 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. 12-RES-JB
    11. 3478
    Prev
    Next
    INDEX
    Explanations

    details of physical altercations and assaults

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances of physical violence and injury

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.96
    inventoryQuantity
    -0.86
    glers
    -0.76
    20439
    -0.75
    values
    -0.69
    tnc
    -0.66
     Trends
    -0.65
    Maps
    -0.64
    idth
    -0.61
     Volunte
    -0.61
    POSITIVE LOGITS
     repeatedly
    1.11
     unconscious
    1.02
     multiple
    0.98
     twice
    0.97
     senseless
    0.91
     several
    0.88
     hard
    0.87
     forcefully
    0.86
     forehead
    0.85
     violently
    0.85
    Activations Density 0.159%

    No Known Activations