© 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. 4-RES-JB
    11. 17137
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences related to violence or physically aggressive actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving the act of "taking out."

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

    No Comments

    Negative Logits
    inski
    -0.75
    anooga
    -0.74
    esa
    -0.74
    NG
    -0.73
    ĸļ
    -0.71
    etsk
    -0.71
    cius
    -0.71
    isma
    -0.69
    BILITY
    -0.67
    oga
    -0.67
    POSITIVE LOGITS
    stretched
    0.86
    fitted
    0.82
    tan
    0.70
    casts
    0.70
    taker
    0.68
    doors
    0.65
    ãĥīãĥ©
    0.64
    worn
    0.62
    shot
    0.62
    sole
    0.61
    Activations Density 0.028%

    No Known Activations