© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 14897
    Prev
    Next
    INDEX
    Explanations

    references to vulnerabilities in software or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.11
    1:0.10
    2:0.05
    3:0.04
    4:0.15
    5:0.02
    6:0.07
    7:0.14
    8:0.02
    9:0.03
    10:0.08
    11:0.14
    Negative Logits
    SpaceEngineers
    -3.15
    ウス
    -2.82
    ymes
    -2.73
    abilia
    -2.65
    �
    -2.55
    seys
    -2.50
    eto
    -2.47
    Í
    -2.46
    �
    -2.43
    Mill
    -2.37
    POSITIVE LOGITS
     vulnerability
    5.40
     CVE
    4.74
     vulnerabilities
    4.72
    CVE
    4.67
     exploit
    4.13
     weakness
    3.79
     flaw
    3.78
     vulner
    3.78
    ulnerability
    3.76
    ulner
    3.71
    Activations Density 0.028%

    No Known Activations