© 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. 9-ATT-KK
    11. 7951
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences of trauma and resilience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.01
    2:0.06
    3:0.04
    4:0.04
    5:0.04
    6:0.28
    7:0.05
    8:0.08
    9:0.21
    10:0.02
    11:0.05
    Negative Logits
    Barn
    -4.32
     Fitz
    -4.14
     Syd
    -4.03
     Texans
    -3.98
    Aust
    -3.94
    �醒
    -3.92
    Met
    -3.91
     Razor
    -3.81
     barn
    -3.80
     Morty
    -3.78
    POSITIVE LOGITS
     Cho
    9.10
     Choi
    8.59
    Cho
    8.29
     Chou
    6.27
    cho
    6.19
     cho
    6.13
     CHO
    5.76
    CHO
    5.40
     Chung
    4.09
    vo
    4.02
    Activations Density 0.003%

    No Known Activations