© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 20570
    Prev
    Next
    INDEX
    Explanations

    the presence of specific names and references to identity or status changes

    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
    0:0.05
    1:0.03
    2:0.07
    3:0.03
    4:0.06
    5:0.04
    6:0.26
    7:0.07
    8:0.09
    9:0.19
    10:0.02
    11:0.04
    Negative Logits
    qs
    -4.22
    Kal
    -3.64
     ba
    -3.63
    MQ
    -3.57
     Kinnikuman
    -3.54
    okane
    -3.48
    Ba
    -3.42
     Omaha
    -3.40
     bait
    -3.39
    ishers
    -3.31
    POSITIVE LOGITS
     Clement
    10.90
    lement
    6.04
     CAR
    4.77
    CAR
    4.20
     cust
    4.15
     Vincent
    4.13
     Levant
    4.05
     Nicol
    4.03
    Car
    3.88
     Nest
    3.87
    Activations Density 0.001%

    No Known Activations