© 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. 10-RES-JB
    11. 12386
    Prev
    Next
    INDEX
    Explanations

    verbs related to prevention, deterrence, or dissuasion

    oai_token-act-pair · gpt-3.5-turbo

    words associated with deterrence and prevention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ammy
    -0.78
    ebus
    -0.74
    emouth
    -0.68
    ships
    -0.67
    ophon
    -0.66
    hare
    -0.65
     quarters
    -0.64
    doms
    -0.62
    eah
    -0.61
     expans
    -0.61
    POSITIVE LOGITS
    ministic
    1.37
    ative
    0.95
    minist
    0.90
    asive
    0.89
    asion
    0.86
    ptive
    0.85
    icide
    0.79
    aneous
    0.79
    rence
    0.77
    atives
    0.74
    Activations Density 0.076%

    No Known Activations