© 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. 22012
    Prev
    Next
    INDEX
    Explanations

    expressions and indicators of controversy or conflict

    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
    0:0.14
    1:0.22
    2:0.04
    3:0.03
    4:0.02
    5:0.02
    6:0.08
    7:0.11
    8:0.06
    9:0.03
    10:0.15
    11:0.05
    Negative Logits
     Explicit
    -2.53
    apo
    -2.51
    thin
    -2.48
    dash
    -2.46
    Clean
    -2.40
     Pure
    -2.37
     Fiesta
    -2.36
    clean
    -2.35
     Hipp
    -2.34
     Clean
    -2.33
    POSITIVE LOGITS
     Lor
    7.02
     Vor
    3.20
    lor
    3.12
    Thor
    2.91
     Kor
    2.86
     Lynd
    2.79
    utor
    2.72
     Gor
    2.65
     Osc
    2.65
     Ort
    2.64
    Activations Density 0.010%

    No Known Activations