© 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. 10-ATT-KK
    11. 14294
    Prev
    Next
    INDEX
    Explanations

    expressions of political affiliations or party references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.17
    1:0.09
    2:0.06
    3:0.05
    4:0.06
    5:0.04
    6:0.11
    7:0.11
    8:0.04
    9:0.05
    10:0.11
    11:0.06
    Negative Logits
     Elder
    -2.94
    ename
    -2.83
     Oracle
    -2.76
    Oracle
    -2.72
     Hansen
    -2.71
     Cthulhu
    -2.69
     Nazi
    -2.60
     sealed
    -2.59
     Jak
    -2.55
     Serbian
    -2.54
    POSITIVE LOGITS
     Louie
    6.92
    Lou
    4.52
     Lou
    3.39
    schild
    2.94
    Mus
    2.84
    Louis
    2.81
     corrid
    2.81
    sonian
    2.75
     Texans
    2.67
    senal
    2.64
    Activations Density 0.000%

    No Known Activations