© 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. 9-RES-JB
    11. 9897
    Prev
    Next
    INDEX
    Explanations

    phrases related to various forms of violence and actions against violence

    oai_token-act-pair · gpt-3.5-turbo

    references to violence and related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Art-related Features
    clicking (!) tells you this explanation was modified by the list author

    No Comments

    Negative Logits
    sonian
    -0.85
    ocular
    -0.82
    é¾įå
    -0.75
    heit
    -0.75
    dit
    -0.74
    arton
    -0.73
    acle
    -0.71
    osition
    -0.68
    oplan
    -0.68
     Folder
    -0.67
    POSITIVE LOGITS
     perpetrated
    1.20
     inflicted
    1.01
     against
    0.93
     directed
    0.91
     prevention
    0.89
     committed
    0.85
     towards
    0.85
     erupted
    0.82
     Against
    0.82
     toward
    0.81
    Activations Density 0.062%

    No Known Activations