© 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. 2962
    Prev
    Next
    INDEX
    Explanations

    sentences containing statements or assertions

    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
    1:0.02
    2:0.05
    3:0.03
    4:0.06
    5:0.04
    6:0.20
    7:0.04
    8:0.11
    9:0.24
    10:0.02
    11:0.04
    Negative Logits
     MF
    -4.39
     Ambro
    -4.10
     appl
    -3.73
    aqu
    -3.69
     Telecom
    -3.47
     Huma
    -3.43
     spam
    -3.43
     tum
    -3.42
     textile
    -3.41
     Yamaha
    -3.34
    POSITIVE LOGITS
     Kirk
    11.55
    irk
    7.20
     Dirk
    5.23
     Spock
    5.15
     Scot
    4.83
    Scot
    4.56
     Allen
    4.56
     Barkley
    4.49
     Kling
    4.45
     McCoy
    4.30
    Activations Density 0.002%

    No Known Activations