© 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. 8258
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and custody issues

    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
    0:0.12
    1:0.14
    2:0.08
    3:0.03
    4:0.03
    5:0.02
    6:0.05
    7:0.10
    8:0.02
    9:0.06
    10:0.24
    11:0.04
    Negative Logits
    VK
    -3.26
    omon
    -3.06
    erk
    -2.68
    uke
    -2.67
    使
    -2.63
    hazard
    -2.52
     Bourbon
    -2.50
    obar
    -2.50
    mur
    -2.49
    lock
    -2.48
    POSITIVE LOGITS
     Si
    9.82
    Si
    8.72
     si
    6.64
    Ti
    5.02
     Ti
    4.83
    si
    4.74
     Ni
    4.61
     Mi
    4.05
     ni
    4.05
     Ci
    3.98
    Activations Density 0.002%

    No Known Activations