© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 15343
    Prev
    Next
    INDEX
    Explanations

    legislative actions and details regarding bills in Congress

    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
    0:0.02
    1:0.03
    2:0.05
    3:0.06
    4:0.08
    5:0.25
    6:0.03
    7:0.08
    8:0.02
    9:0.27
    10:0.02
    11:0.05
    Negative Logits
    gotten
    -2.40
     tended
    -2.27
    pired
    -2.25
    peak
    -2.22
     arise
    -2.21
    POSE
    -2.20
    hemer
    -2.08
    =-=-=-=-=-=-=-=-
    -2.07
     Appears
    -2.05
     extraord
    -2.01
    POSITIVE LOGITS
    votes
    2.56
     unanimously
    2.47
    packing
    2.47
     Judiciary
    2.36
     veto
    2.27
     before
    2.14
    ゼウス
    2.14
    ventus
    2.12
    ards
    2.11
    nesota
    2.07
    Activations Density 0.048%

    No Known Activations