© 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. 1-RES-JB
    11. 5732
    Prev
    Next
    INDEX
    Explanations

    mentions of antivirus software and computer viruses

    oai_token-act-pair · gpt-3.5-turbo

    terms related to computer viruses and cybersecurity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ezvous
    -0.74
    erent
    -0.74
    erer
    -0.72
    cussion
    -0.69
    taboola
    -0.68
    fried
    -0.67
    tall
    -0.67
    igree
    -0.65
    itent
    -0.65
    uscript
    -0.64
    POSITIVE LOGITS
    irus
    1.33
    unia
    0.75
     scanners
    0.74
     CTR
    0.70
    oice
    0.70
     advis
    0.70
     scanner
    0.68
     AVG
    0.68
     PowerShell
    0.67
    osate
    0.67
    Activations Density 0.014%

    No Known Activations