© 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. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 40507
    Prev
    Next
    INDEX
    Explanations

    references to hacking incidents or cybersecurity breaches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.02
    2:0.04
    3:0.04
    4:0.04
    5:0.04
    6:0.02
    7:0.04
    8:0.02
    9:0.08
    10:0.47
    11:0.12
    Negative Logits
     Nursing
    -1.61
    �
    -1.59
     pronunciation
    -1.55
    ikk
    -1.53
     nurses
    -1.52
     relegation
    -1.47
     Breakfast
    -1.46
     apprentices
    -1.46
     maternity
    -1.45
     Happiness
    -1.44
    POSITIVE LOGITS
     malware
    2.35
    DoS
    2.21
     ransomware
    2.13
     malicious
    1.95
     hackers
    1.90
     attackers
    1.83
     hacker
    1.82
    ionage
    1.82
     exploit
    1.80
     hoax
    1.80
    Activations Density 0.583%

    No Known Activations