© 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. 17561
    Prev
    Next
    INDEX
    Explanations

    references to political candidates and their associated controversies or allegations

    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
    0:0.12
    1:0.01
    2:0.16
    3:0.07
    4:0.03
    5:0.10
    6:0.05
    7:0.06
    8:0.28
    9:0.02
    10:0.02
    11:0.02
    Negative Logits
    án
    -3.82
    sson
    -3.81
    ETF
    -3.52
    �
    -3.51
     Sabres
    -3.35
    ás
    -3.29
     Czech
    -3.24
    ín
    -3.24
     Mei
    -3.22
    Hong
    -3.15
    POSITIVE LOGITS
     Alabama
    5.10
     Moore
    4.72
    Alabama
    4.39
    Moore
    4.34
     accuser
    3.79
     evangelical
    3.53
     Roy
    3.51
     Ala
    3.48
     accus
    3.46
     biblical
    3.45
    Activations Density 0.018%

    No Known Activations