© 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. 9-ATT-KK
    6. 18954
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and political themes involving contracts and actions taken by authorities

    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
    0:0.10
    1:0.03
    2:0.05
    3:0.25
    4:0.04
    5:0.18
    6:0.01
    7:0.06
    8:0.05
    9:0.02
    10:0.12
    11:0.05
    Negative Logits
     likened
    -2.23
     tasted
    -2.23
    龍
    -1.91
     residual
    -1.91
     inscribed
    -1.89
     sensed
    -1.79
     measured
    -1.79
     liberated
    -1.79
     precip
    -1.78
     deteriorated
    -1.78
    POSITIVE LOGITS
     Tags
    2.15
     Taxes
    2.12
     Emails
    2.08
    Politics
    2.04
     Videos
    1.96
    quest
    1.95
     Posts
    1.94
     Admin
    1.90
     Politics
    1.85
     google
    1.84
    Activations Density 0.004%

    No Known Activations