© 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 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. 6-RES-JB
    11. 14749
    Prev
    Next
    INDEX
    Explanations

    phrases related to cyber attacks and security breaches

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to cyber attacks and security incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ikk
    -0.88
    cellence
    -0.75
    essional
    -0.74
    union
    -0.73
    united
    -0.72
     Yards
    -0.69
    addle
    -0.69
     Negro
    -0.69
    stairs
    -0.68
    rentices
    -0.68
    POSITIVE LOGITS
     malware
    1.38
    DoS
    1.24
     ransomware
    1.22
     hackers
    1.20
     CVE
    1.13
     hacker
    1.09
     exploit
    1.08
    CVE
    1.07
    WARE
    1.04
     adversary
    1.02
    Activations Density 0.401%

    No Known Activations