© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 1737
    Prev
    Next
    INDEX
    Explanations

    references to advocacy groups and political organizations

    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
    0:0.19
    1:0.07
    2:0.09
    3:0.09
    4:0.08
    5:0.04
    6:0.01
    7:0.09
    8:0.05
    9:0.01
    10:0.21
    11:0.02
    Negative Logits
    ノ
    -2.30
    Textures
    -2.23
    ioxid
    -2.17
     perman
    -2.16
    ciation
    -2.13
    endi
    -2.09
     stagnation
    -2.08
    mega
    -2.06
    amins
    -2.04
     ILCS
    -2.04
    POSITIVE LOGITS
     testified
    3.51
     commented
    3.10
     responded
    3.05
     criticized
    2.93
     tweeted
    2.91
     contacted
    2.91
     spoke
    2.85
     traveled
    2.84
     stormed
    2.82
     apologized
    2.77
    Activations Density 0.132%

    No Known Activations