© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 13729
    Prev
    Next
    INDEX
    Explanations

    phrases depicting violent actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of violent actions or attacks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.92
    imester
    -0.81
    inventoryQuantity
    -0.76
    iterranean
    -0.72
    iHUD
    -0.70
    Factor
    -0.69
     Conversation
    -0.68
    arenthood
    -0.67
    glers
    -0.66
    YC
    -0.66
    POSITIVE LOGITS
     senseless
    1.23
     unconscious
    1.10
     merciless
    1.04
     harder
    1.02
     violently
    1.02
     repeatedly
    1.01
     inappropriately
    0.98
     furiously
    0.95
     hard
    0.93
     hardest
    0.91
    Activations Density 0.154%

    No Known Activations