© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 22776
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial terms and agreements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    financial and collateral terms related to risk and loss

    oai_token-act-pair · gpt-4o-miniTriggered 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
    0:0.05
    1:0.04
    2:0.17
    3:0.04
    4:0.26
    5:0.06
    6:0.03
    7:0.04
    8:0.07
    9:0.11
    10:0.05
    11:0.03
    Negative Logits
    rake
    -1.50
    leck
    -1.45
    yton
    -1.44
     Jelly
    -1.42
    urnal
    -1.38
    acan
    -1.37
     lantern
    -1.34
     Lantern
    -1.32
     Winc
    -1.32
     CFL
    -1.29
    POSITIVE LOGITS
    iation
    1.61
     exhaustion
    1.30
     Extensions
    1.30
    orem
    1.27
    ternity
    1.25
     ratification
    1.25
    Asset
    1.25
     consequential
    1.23
    в
    1.21
    *:
    1.21
    Activations Density 0.002%

    No Known Activations