© 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. 10-ATT-KK
    11. 7348
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate underlying threats or vulnerabilities in technology

    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
    0:0.08
    1:0.10
    2:0.04
    3:0.07
    4:0.05
    5:0.04
    6:0.05
    7:0.27
    8:0.03
    9:0.05
    10:0.10
    11:0.07
    Negative Logits
     Hamp
    -2.87
     Giles
    -2.62
     Hert
    -2.62
     Gunn
    -2.60
     Compass
    -2.46
    issance
    -2.45
    romeda
    -2.44
     Hammond
    -2.27
     Hastings
    -2.26
     Firefly
    -2.25
    POSITIVE LOGITS
     patented
    2.98
    trade
    2.42
     porous
    2.42
    aten
    2.33
    cakes
    2.29
    ervatives
    2.24
     untreated
    2.23
    Trade
    2.21
     proprietary
    2.21
     tuber
    2.20
    Activations Density 0.003%

    No Known Activations