© 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. 9-ATT-KK
    11. 718
    Prev
    Next
    INDEX
    Explanations

    concepts related to political challenges and legal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.01
    2:0.06
    3:0.23
    4:0.01
    5:0.06
    6:0.01
    7:0.05
    8:0.02
    9:0.01
    10:0.41
    11:0.01
    Negative Logits
     praised
    -2.17
     enhances
    -2.02
    azines
    -2.02
     promotes
    -2.01
     originated
    -1.96
     blends
    -1.92
     conserve
    -1.90
     donated
    -1.90
     Favorite
    -1.88
    Favorite
    -1.87
    POSITIVE LOGITS
     dilemma
    3.18
    chall
    3.12
     looming
    3.10
     uphill
    3.02
     repercussions
    3.01
     peril
    2.99
     consequences
    2.90
     challenges
    2.88
     challenge
    2.88
     predicament
    2.73
    Activations Density 0.180%

    No Known Activations