© 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. 12256
    Prev
    Next
    INDEX
    Explanations

    content related to politics and current events, particularly focusing on rallies, political campaigns, and social commentary

    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
    0:0.03
    1:0.13
    2:0.06
    3:0.08
    4:0.05
    5:0.12
    6:0.06
    7:0.06
    8:0.08
    9:0.11
    10:0.10
    11:0.06
    Negative Logits
    ulton
    -1.24
    ilogy
    -1.17
    SPONSORED
    -1.14
     glim
    -1.08
     independents
    -1.06
    ettle
    -1.02
    monds
    -1.02
    ingham
    -0.99
    olicy
    -0.98
     needing
    -0.98
    POSITIVE LOGITS
    ğ
    1.59
    ikan
    1.46
    ipedia
    1.41
     XD
    1.38
    ku
    1.23
     Cheong
    1.23
     [+
    1.21
    gur
    1.19
    hai
    1.19
    �
    1.17
    Activations Density 0.537%

    No Known Activations