© 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. 12599
    Prev
    Next
    INDEX
    Explanations

    detected security incidents and references to organizations connected to security measures

    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
    0:0.07
    1:0.22
    2:0.08
    3:0.04
    4:0.03
    5:0.01
    6:0.09
    7:0.11
    8:0.08
    9:0.02
    10:0.18
    11:0.03
    Negative Logits
    stanbul
    -2.89
    phrine
    -2.86
     Tanz
    -2.72
    ロ
    -2.72
     Rou
    -2.65
    abin
    -2.52
    Ge
    -2.48
     Rohing
    -2.48
    byn
    -2.46
     Ge
    -2.43
    POSITIVE LOGITS
     Inc
    6.00
     inc
    5.09
    inc
    5.04
    Inc
    4.99
     INC
    4.83
    INC
    4.64
     Indigo
    3.02
     Corp
    2.92
     LLC
    2.91
     Ign
    2.85
    Activations Density 0.006%

    No Known Activations