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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 21812
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate actions or suggestions to look at something

    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
    0:0.04
    1:0.02
    2:0.04
    3:0.25
    4:0.03
    5:0.12
    6:0.02
    7:0.06
    8:0.03
    9:0.02
    10:0.23
    11:0.08
    Negative Logits
    taboola
    -2.03
     appealed
    -2.01
     risked
    -2.01
     interfered
    -1.97
     violated
    -1.83
     persisted
    -1.83
     hampered
    -1.81
     journals
    -1.78
     canceled
    -1.77
     deteriorating
    -1.74
    POSITIVE LOGITS
    ̶
    3.23
    .—
    2.48
    ————————
    2.45
    =(
    2.41
    ¨
    2.35
    …..
    2.34
    …………
    2.32
    ォ
    2.32
    .):
    2.32
    ####
    2.31
    Activations Density 0.062%

    No Known Activations