© 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. 10-ATT-KK
    11. 15395
    Prev
    Next
    INDEX
    Explanations

    instances of political party names and affiliations

    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
    0:0.07
    1:0.05
    2:0.04
    3:0.06
    4:0.08
    5:0.02
    6:0.16
    7:0.15
    8:0.02
    9:0.06
    10:0.16
    11:0.08
    Negative Logits
     Bans
    -3.10
     VC
    -3.08
     BCC
    -2.96
     Vand
    -2.95
     Kenyan
    -2.82
     Somali
    -2.81
    wcs
    -2.77
     Prosecut
    -2.74
     Lawyers
    -2.71
     Vanderbilt
    -2.68
    POSITIVE LOGITS
    angible
    3.04
    dor
    2.98
    ngth
    2.83
    ér
    2.83
    quart
    2.73
    hazard
    2.64
    blance
    2.63
    azard
    2.61
    APH
    2.60
    oire
    2.59
    Activations Density 0.004%

    No Known Activations