© 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. 3-RES-JB
    11. 9775
    Prev
    Next
    INDEX
    Explanations

    terms related to physical aggression and violence

    oai_token-act-pair · gpt-3.5-turbo

    references to violent actions, particularly assaults and related offenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocular
    -0.70
     CFR
    -0.67
    FORE
    -0.66
    ãĤ©
    -0.65
     Solitaire
    -0.64
     snipp
    -0.64
    printed
    -0.63
     TIT
    -0.62
     optimizing
    -0.62
    ETA
    -0.61
    POSITIVE LOGITS
     assault
    0.96
    uous
    0.89
    uously
    0.87
     assaults
    0.86
    entimes
    0.83
    quit
    0.82
    ively
    0.81
     Assault
    0.80
    assault
    0.77
    quez
    0.76
    Activations Density 0.015%

    No Known Activations