© 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. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 10618
    Prev
    Next
    INDEX
    Explanations

    references to cybersecurity threats and vulnerabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.06
    2:0.05
    3:0.03
    4:0.12
    5:0.15
    6:0.08
    7:0.08
    8:0.07
    9:0.06
    10:0.10
    11:0.08
    Negative Logits
    opolis
    -1.40
     solitude
    -1.31
     Cinderella
    -1.30
    undrum
    -1.26
     ridden
    -1.26
     ladies
    -1.25
     etiquette
    -1.24
    iggurat
    -1.23
    icult
    -1.23
    comfort
    -1.22
    POSITIVE LOGITS
     Forensic
    1.74
     antiv
    1.61
     LIA
    1.57
    bda
    1.55
    crypt
    1.54
     malware
    1.54
    cot
    1.50
    mite
    1.49
     SHA
    1.47
     malicious
    1.47
    Activations Density 0.232%

    No Known Activations