© 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. 2-ATT-KK
    11. 22556
    Prev
    Next
    INDEX
    Explanations

    security-related terms and phrases, especially focusing on incidents, policies, and technology

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    terms related to security, risk management, and oversight in cybersecurity contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.02
    2:0.32
    3:0.05
    4:0.09
    5:0.07
    6:0.02
    7:0.02
    8:0.03
    9:0.20
    10:0.05
    11:0.02
    Negative Logits
    姫
    -1.43
    エル
    -1.43
    zeb
    -1.32
    ydia
    -1.31
     Unch
    -1.29
    gyn
    -1.28
    ItemImage
    -1.23
    ーク
    -1.22
    cair
    -1.20
    pless
    -1.20
    POSITIVE LOGITS
    ForgeModLoader
    1.47
    ERT
    1.40
    warts
    1.39
    VICE
    1.29
    pert
    1.29
    riors
    1.25
     CTR
    1.25
     infiltration
    1.24
     Greenwald
    1.24
    Security
    1.22
    Activations Density 0.039%

    No Known Activations