© 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. 9-ATT-KK
    6. 10595
    Prev
    Next
    INDEX
    Explanations

    sentences involving authority figures making statements or taking actions

    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
    0:0.08
    1:0.03
    2:0.06
    3:0.04
    4:0.06
    5:0.03
    6:0.21
    7:0.04
    8:0.07
    9:0.27
    10:0.02
    11:0.02
    Negative Logits
     Staples
    -4.40
     Stamp
    -4.03
    ROM
    -3.92
    kered
    -3.87
     printer
    -3.64
     Globe
    -3.58
     Ribbon
    -3.56
     ripple
    -3.49
     ROM
    -3.37
    olina
    -3.33
    POSITIVE LOGITS
    Ak
    9.67
     Ak
    9.63
     ak
    7.87
     Ack
    7.15
     AK
    6.18
    AK
    5.88
    ak
    4.99
     Bak
    4.88
     Akira
    4.79
    Ark
    4.63
    Activations Density 0.004%

    No Known Activations