© 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. 18805
    Prev
    Next
    INDEX
    Explanations

    numerical data and references related to statistics or ratings

    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
    0:0.07
    1:0.02
    2:0.03
    3:0.18
    4:0.22
    5:0.15
    6:0.03
    7:0.12
    8:0.06
    9:0.02
    10:0.03
    11:0.03
    Negative Logits
     Stall
    -2.10
     RAID
    -2.10
     Tribe
    -2.00
     Cutter
    -1.95
     Cruise
    -1.91
     WCS
    -1.89
    trap
    -1.88
     TRI
    -1.80
     wrench
    -1.80
     UR
    -1.79
    POSITIVE LOGITS
    edin
    2.53
    Magazine
    2.52
    dden
    2.15
    inburgh
    2.12
    Appearances
    2.10
    earances
    2.06
    ettings
    2.03
    ences
    2.02
    eeds
    2.00
    iona
    1.96
    Activations Density 0.000%

    No Known Activations