© 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. 7-RES-JB
    11. 3194
    Prev
    Next
    INDEX
    Explanations

    descriptions related to violent or harmful actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "brutal" in contexts related to violence or suffering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    leaf
    -0.87
    ploma
    -0.77
    ource
    -0.77
    cript
    -0.76
    verage
    -0.75
    OPLE
    -0.74
    clips
    -0.74
    BU
    -0.71
    arten
    -0.71
    Recommend
    -0.71
    POSITIVE LOGITS
     assault
    1.03
    ized
    1.01
     assaults
    0.97
     murders
    0.95
     torture
    0.93
    izing
    0.92
     punishments
    0.91
     beasts
    0.89
     murder
    0.85
     retribution
    0.84
    Activations Density 0.040%

    No Known Activations