© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 19462
    Prev
    Next
    INDEX
    Explanations

    references to staff, particularly in positions of authority or influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.03
    2:0.20
    3:0.05
    4:0.08
    5:0.03
    6:0.20
    7:0.06
    8:0.03
    9:0.02
    10:0.07
    11:0.15
    Negative Logits
    warm
    -1.66
    pell
    -1.61
    utical
    -1.60
    inventoryQuantity
    -1.54
    ecycle
    -1.45
    issance
    -1.40
     briefings
    -1.38
     payroll
    -1.36
     fronts
    -1.34
     forefront
    -1.30
    POSITIVE LOGITS
    itone
    1.32
     opio
    1.32
     unden
    1.30
     needles
    1.23
     Receiver
    1.22
    aez
    1.20
    Route
    1.18
    ixt
    1.17
    Brit
    1.17
     TRAN
    1.16
    Activations Density 0.001%

    No Known Activations