© 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. 21093
    Prev
    Next
    INDEX
    Explanations

    mentions of cultural or social trends related to lifestyle products and behaviors

    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
    1:0.01
    2:0.04
    3:0.06
    4:0.08
    5:0.41
    6:0.02
    7:0.03
    8:0.01
    9:0.20
    10:0.01
    11:0.05
    Negative Logits
     DOES
    -3.21
    would
    -2.97
     wouldn
    -2.84
     beforehand
    -2.67
    "/>
    -2.67
     would
    -2.62
    Otherwise
    -2.61
    thens
    -2.60
    }"
    -2.60
     lasts
    -2.60
    POSITIVE LOGITS
     increasingly
    4.44
     again
    3.49
     becoming
    3.40
     dramatically
    3.35
     considerably
    3.30
     more
    3.28
     replaced
    3.09
     redesigned
    3.07
    increasing
    3.03
     markedly
    3.00
    Activations Density 0.937%

    No Known Activations