© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 18457
    Prev
    Next
    INDEX
    Explanations

    references to events involving large gatherings and associated actions or reactions

    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
    0:0.12
    1:0.07
    2:0.09
    3:0.05
    4:0.02
    5:0.03
    6:0.10
    7:0.02
    8:0.02
    9:0.39
    10:0.03
    11:0.02
    Negative Logits
     Briggs
    -4.02
     Bridge
    -3.36
     Spac
    -3.35
     Sweeney
    -3.33
     NAD
    -3.23
    Bridge
    -3.18
     Leslie
    -3.17
    Syn
    -3.15
     McCarthy
    -3.12
     bund
    -3.10
    POSITIVE LOGITS
     Taken
    4.79
     retake
    4.69
    take
    4.48
     Takes
    4.34
     taken
    4.30
     Take
    4.25
    taking
    4.14
     Taking
    4.05
    Take
    4.00
     taking
    3.99
    Activations Density 0.054%

    No Known Activations