© 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. 14237
    Prev
    Next
    INDEX
    Explanations

    patterns related to political statements and positions

    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
    0:0.05
    1:0.02
    2:0.06
    3:0.22
    4:0.03
    5:0.04
    6:0.02
    7:0.05
    8:0.02
    9:0.02
    10:0.40
    11:0.02
    Negative Logits
    ��
    -2.76
    cedented
    -2.50
    almost
    -2.31
    redibly
    -2.17
     extensively
    -2.12
    orest
    -2.11
    reet
    -2.09
     twice
    -2.09
    surprisingly
    -2.02
    umerous
    -2.00
    POSITIVE LOGITS
     decides
    2.35
     arises
    2.25
     happens
    2.15
    Whatever
    2.05
     might
    2.02
     failings
    1.99
    Wr
    1.98
     swayed
    1.98
     emerges
    1.97
     ends
    1.96
    Activations Density 0.066%

    No Known Activations