© 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. 2-ATT-KK
    11. 12515
    Prev
    Next
    INDEX
    Explanations

    phrases related to political elections or terms related to political activity

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.01
    2:0.30
    3:0.09
    4:0.21
    5:0.03
    6:0.04
    7:0.02
    8:0.07
    9:0.07
    10:0.04
    11:0.02
    Negative Logits
    ulhu
    -1.43
     Glover
    -1.29
    Magikarp
    -1.19
     Liver
    -1.19
     Grade
    -1.19
     Lily
    -1.19
     Sop
    -1.18
     Fraud
    -1.16
    gram
    -1.16
     warranted
    -1.15
    POSITIVE LOGITS
    issance
    1.73
     spons
    1.64
    itory
    1.60
    untled
    1.57
    quit
    1.53
    paren
    1.46
    arching
    1.41
    join
    1.39
    ardless
    1.35
    IDA
    1.33
    Activations Density 0.022%

    No Known Activations