© 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. 9-RES-JB
    11. 11171
    Prev
    Next
    INDEX
    Explanations

    words related to violent actions like executions, beheadings, and decapitations

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to violent actions and methods of execution

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Balt
    -0.77
    CRE
    -0.76
    natureconservancy
    -0.70
     explan
    -0.70
    RW
    -0.70
     ECO
    -0.68
    paren
    -0.68
    BuyableInstoreAndOnline
    -0.68
    soType
    -0.67
    ĨĴ
    -0.65
    POSITIVE LOGITS
     wounds
    0.88
    ings
    0.85
    ography
    0.85
     inflicted
    0.82
     corpses
    0.82
     decap
    0.79
    nikov
    0.77
     carc
    0.75
     alive
    0.75
     unarmed
    0.74
    Activations Density 0.226%

    No Known Activations