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

    Neuronpedia

    Jacobian LensNEW
    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. 10-ATT-KK
    11. 15276
    Prev
    Next
    INDEX
    Explanations

    references to social groups and their dynamics in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.02
    2:0.03
    3:0.04
    4:0.08
    5:0.44
    6:0.02
    7:0.03
    8:0.02
    9:0.20
    10:0.01
    11:0.03
    Negative Logits
    ILA
    -3.06
    =[
    -2.96
    =#
    -2.95
    Said
    -2.87
    ELD
    -2.73
    forcement
    -2.68
    ={
    -2.57
    VERTISEMENT
    -2.56
    ilan
    -2.55
    Reviewer
    -2.45
    POSITIVE LOGITS
     rely
    4.03
     nowadays
    3.61
     aren
    3.43
     ignore
    3.29
     seem
    3.22
     confuse
    3.21
     originate
    3.20
     reside
    3.20
     refuse
    3.17
     don
    3.17
    Activations Density 0.465%

    No Known Activations