© 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. 11-RES-JB
    11. 20847
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical altercations and conflicts

    oai_token-act-pair · gpt-3.5-turbo

    instances of violence or physical altercations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    ngth
    -0.75
    oliberal
    -0.72
     preference
    -0.69
     implants
    -0.66
    erton
    -0.66
     cert
    -0.65
    algia
    -0.65
     biases
    -0.64
    Reviewer
    -0.64
    20439
    -0.63
    POSITIVE LOGITS
     ensued
    1.45
     erupted
    1.19
     erupt
    1.11
     escalated
    1.08
     pandemonium
    1.04
     escalate
    0.96
     escalating
    0.95
     ens
    0.95
     escal
    0.94
     between
    0.93
    Activations Density 0.327%

    No Known Activations