Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 10748
    Prev
    Next
    INDEX
    Explanations

    terms related to financial incentives and corporate accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.08
    2:0.38
    3:0.02
    4:0.02
    5:0.03
    6:0.07
    7:0.05
    8:0.06
    9:0.04
    10:0.07
    11:0.07
    Negative Logits
     Courier
    -1.22
     pity
    -1.13
     Tablet
    -1.01
     Rescue
    -1.00
     Sail
    -0.96
     Garrison
    -0.96
     Refuge
    -0.96
    oday
    -0.95
     fault
    -0.95
     Forth
    -0.95
    POSITIVE LOGITS
    isphere
    1.52
    eas
    1.33
    licks
    1.32
    pages
    1.23
    nces
    1.16
    appers
    1.16
    gotten
    1.13
    appings
    1.12
     outl
    1.10
    hetic
    1.07
    Activations Density 0.114%

    No Known Activations