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. 10032
    Prev
    Next
    INDEX
    Explanations

    phrases related to prominence or importance

    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
    1:0.05
    2:0.12
    3:0.02
    4:0.04
    5:0.05
    6:0.11
    7:0.09
    8:0.10
    9:0.15
    10:0.10
    11:0.07
    Negative Logits
     pockets
    -1.00
    ocks
    -0.93
    ioxid
    -0.92
    ribut
    -0.91
    =~=~
    -0.90
    ONEY
    -0.89
     underage
    -0.89
    $.
    -0.88
    ateral
    -0.86
     unsuspecting
    -0.86
    POSITIVE LOGITS
     summarizes
    1.16
     sprang
    1.11
     belongs
    1.08
     meanwhile
    1.05
     swayed
    1.01
     comprises
    0.99
     moreover
    0.99
     Libre
    0.98
    BIP
    0.95
     Tuc
    0.94
    Activations Density 0.151%

    No Known Activations