© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 8779
    Prev
    Next
    INDEX
    Explanations

    details related to restraints and their use in public schools, particularly involving students and incidents of abuse or injuries

    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
    0:0.13
    1:0.06
    2:0.04
    3:0.05
    4:0.08
    5:0.03
    6:0.09
    7:0.22
    8:0.03
    9:0.05
    10:0.08
    11:0.09
    Negative Logits
     Dwar
    -2.31
    ı
    -2.27
    pell
    -2.24
    udic
    -2.19
    ivalry
    -2.14
    ß
    -2.10
     Ruin
    -2.09
     Shal
    -2.08
     UNESCO
    -2.03
    agh
    -2.03
    POSITIVE LOGITS
     restraints
    3.22
     shack
    2.88
     handcuffed
    2.86
     cuff
    2.78
     handc
    2.77
     handcuffs
    2.73
     strapped
    2.48
     interrogated
    2.45
     restrained
    2.44
     taped
    2.40
    Activations Density 0.007%

    No Known Activations