© 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 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. 2-RES-JB
    11. 22346
    Prev
    Next
    INDEX
    Explanations

    words related to violent or harsh actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "brutal" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OPLE
    -0.80
    ership
    -0.74
    rote
    -0.73
    ploma
    -0.72
    FU
    -0.71
    Script
    -0.71
    cript
    -0.71
    annis
    -0.70
    ople
    -0.68
    Recommend
    -0.68
    POSITIVE LOGITS
     earthqu
    1.02
     beasts
    0.92
    ized
    0.89
     killers
    0.86
     savage
    0.82
     brutal
    0.81
     assault
    0.81
     torture
    0.80
     brutality
    0.80
     devast
    0.79
    Activations Density 0.015%

    No Known Activations