© 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. 23336
    Prev
    Next
    INDEX
    Explanations

    phrases indicating endorsements or support in a political context

    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
    0:0.08
    1:0.02
    2:0.04
    3:0.03
    4:0.07
    5:0.04
    6:0.15
    7:0.05
    8:0.08
    9:0.32
    10:0.02
    11:0.04
    Negative Logits
     desert
    -3.86
     Desert
    -3.82
    issan
    -3.76
    gypt
    -3.56
     Butterfly
    -3.27
     Chilean
    -3.19
    arget
    -3.13
    vez
    -3.07
    dragon
    -3.00
    adium
    -2.97
    POSITIVE LOGITS
     O
    5.54
    O
    5.01
     OU
    4.37
     OC
    4.27
     Oxy
    4.13
     OD
    3.96
     Ou
    3.92
     Om
    3.89
     Otto
    3.89
     Ober
    3.86
    Activations Density 0.022%

    No Known Activations