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. 9-ATT-KK
    6. 11213
    Prev
    Next
    INDEX
    Explanations

    references to giving and receiving transactions, particularly in an economic context

    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
    0:0.11
    1:0.04
    2:0.10
    3:0.17
    4:0.03
    5:0.11
    6:0.03
    7:0.17
    8:0.06
    9:0.02
    10:0.08
    11:0.02
    Negative Logits
    DragonMagazine
    -2.09
    oubted
    -2.00
    asa
    -1.95
     HERO
    -1.91
    blance
    -1.90
    ovie
    -1.89
    soDeliveryDate
    -1.88
    apan
    -1.86
    campaign
    -1.84
     Defenders
    -1.84
    POSITIVE LOGITS
     appra
    2.20
     yourself
    2.03
     slowly
    1.99
     politely
    1.97
     suddenly
    1.96
     bumps
    1.94
     recomp
    1.92
     accidentally
    1.92
     gradually
    1.90
     adjustment
    1.88
    Activations Density 0.058%

    No Known Activations