© 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. 21374
    Prev
    Next
    INDEX
    Explanations

    references to dangerous or violent incidents involving animals

    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
    0:0.09
    1:0.24
    2:0.06
    3:0.04
    4:0.04
    5:0.03
    6:0.07
    7:0.09
    8:0.03
    9:0.04
    10:0.20
    11:0.03
    Negative Logits
     Masquerade
    -3.02
     Monk
    -2.98
     Artemis
    -2.89
    oco
    -2.85
     GF
    -2.79
     Chloe
    -2.75
    Whit
    -2.71
    throp
    -2.65
     XV
    -2.62
     QC
    -2.58
    POSITIVE LOGITS
     Ir
    8.82
    Ir
    7.84
     ir
    6.01
     Il
    4.64
     Irwin
    4.36
    ir
    4.18
     IR
    4.13
    Bir
    3.71
     Irving
    3.70
    IR
    3.59
    Activations Density 0.005%

    No Known Activations