© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10941
    Prev
    Next
    INDEX
    Explanations

    discussions about political parties and their dynamics

    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
    0:0.13
    1:0.02
    2:0.14
    3:0.12
    4:0.03
    5:0.08
    6:0.04
    7:0.07
    8:0.25
    9:0.02
    10:0.02
    11:0.04
    Negative Logits
     Compton
    -2.72
     spr
    -2.61
     OCD
    -2.58
     Neural
    -2.54
     Halo
    -2.46
     Geh
    -2.45
    RECT
    -2.40
    meter
    -2.37
     Owens
    -2.36
     curv
    -2.35
    POSITIVE LOGITS
    Party
    4.57
    Lenin
    4.52
     UKIP
    4.09
     electoral
    3.98
     socialists
    3.98
     parliamentary
    3.96
     Lenin
    3.96
     Communists
    3.81
     Party
    3.78
     communists
    3.77
    Activations Density 0.099%

    No Known Activations