© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 14301
    Prev
    Next
    INDEX
    Explanations

    references to legal or personal conflicts involving allegations and testimonies related to assault

    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
    0:0.10
    1:0.18
    2:0.06
    3:0.02
    4:0.03
    5:0.01
    6:0.08
    7:0.12
    8:0.02
    9:0.03
    10:0.25
    11:0.04
    Negative Logits
    ahime
    -2.85
    irk
    -2.81
     Wak
    -2.68
    ahu
    -2.64
     Pap
    -2.58
    CVE
    -2.53
    �
    -2.52
    ILA
    -2.50
    uania
    -2.50
    othal
    -2.49
    POSITIVE LOGITS
     Bro
    8.75
    Bro
    7.27
     bro
    6.76
    bro
    6.18
     broom
    3.63
     Schro
    3.60
     Bre
    3.58
     Bros
    3.49
     Brooks
    3.49
    BR
    3.47
    Activations Density 0.016%

    No Known Activations