© 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. 11-RES-JB
    11. 7844
    Prev
    Next
    INDEX
    Explanations

    references to malware and cyberattacks

    oai_token-act-pair · gpt-3.5-turbo

    references to specific types of malware and ransomware

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĶĢâĶĢâĶĢâĶĢ
    -0.91
    ajor
    -0.85
    ikk
    -0.85
     Connie
    -0.83
    aukee
    -0.81
     Garner
    -0.78
    inement
    -0.78
    Ë
    -0.75
    âĪ
    -0.75
    Rachel
    -0.72
    POSITIVE LOGITS
     malware
    1.96
     ransomware
    1.72
     malicious
    1.68
     infected
    1.55
     infect
    1.47
     Virus
    1.47
     antiv
    1.41
     Trojan
    1.39
    CVE
    1.37
     CVE
    1.35
    Activations Density 0.304%

    No Known Activations