© 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. 3-RES-JB
    11. 22964
    Prev
    Next
    INDEX
    Explanations

    words associated with computer hacking activities

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to security or protection against external threats

    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
    atin
    -0.91
    lication
    -0.77
    aches
    -0.76
    arine
    -0.74
    urgy
    -0.73
    metics
    -0.72
    eness
    -0.71
    idine
    -0.70
    clusion
    -0.70
    metic
    -0.70
    POSITIVE LOGITS
    WAYS
    0.76
     archaeologists
    0.74
    DragonMagazine
    0.71
    CDC
    0.71
    ORN
    0.70
     scientists
    0.69
    ĺħ
    0.68
    VID
    0.68
    çīĪ
    0.66
     Canaver
    0.66
    Activations Density 0.000%

    No Known Activations