© 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. 3-RES-JB
    11. 17803
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "torture"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of torture

    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
     Darkness
    -0.72
     magnification
    -0.72
     brightest
    -0.68
     donor
    -0.67
     Active
    -0.66
    lihood
    -0.65
    ACP
    -0.64
     EntityItem
    -0.64
     Silk
    -0.62
     ECB
    -0.62
    POSITIVE LOGITS
    urous
    1.43
    oise
    1.32
    illas
    1.11
    ured
    1.06
    uring
    1.05
    urers
    1.03
     tort
    0.99
    uous
    0.96
    isec
    0.96
    ures
    0.96
    Activations Density 0.005%

    No Known Activations