© 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. 18836
    Prev
    Next
    INDEX
    Explanations

    elements related to events and their occurrence or patterns

    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
    0:0.30
    1:0.02
    2:0.19
    3:0.10
    4:0.03
    5:0.06
    6:0.03
    7:0.06
    8:0.05
    9:0.03
    10:0.07
    11:0.02
    Negative Logits
    phabet
    -2.73
     thicker
    -2.44
    Len
    -2.41
    pent
    -2.41
    Pen
    -2.38
    otomy
    -2.37
    anty
    -2.36
     thinner
    -2.35
     Thin
    -2.34
    bedroom
    -2.29
    POSITIVE LOGITS
    events
    6.25
     Events
    5.80
     events
    5.62
     Event
    5.43
    Event
    5.37
     event
    5.32
    Events
    5.19
    event
    5.07
     EVENT
    4.87
     organisers
    4.22
    Activations Density 0.144%

    No Known Activations