© 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. 6938
    Prev
    Next
    INDEX
    Explanations

    adjectives related to cruelty

    oai_token-act-pair · gpt-3.5-turbo

    references to cruelty or inhumane treatment

    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
     Bundle
    -0.76
     Banking
    -0.75
    ACP
    -0.74
    inoa
    -0.71
    ainers
    -0.71
    aintain
    -0.71
     Starter
    -0.69
    icans
    -0.69
    BU
    -0.68
    CHAT
    -0.65
    POSITIVE LOGITS
     cruel
    0.94
     cruelty
    0.90
    terday
    0.77
     irony
    0.76
    gling
    0.75
     Cruel
    0.74
     inhuman
    0.73
    blooded
    0.73
    est
    0.72
    bones
    0.69
    Activations Density 0.012%

    No Known Activations