© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 21683
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions and claims

    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
    0:0.06
    1:0.10
    2:0.07
    3:0.20
    4:0.03
    5:0.03
    6:0.08
    7:0.09
    8:0.03
    9:0.03
    10:0.19
    11:0.03
    Negative Logits
     metab
    -2.90
     Wein
    -2.74
    renheit
    -2.64
     McM
    -2.64
    Pal
    -2.46
     Carroll
    -2.37
    agara
    -2.34
     Zam
    -2.33
    gnu
    -2.31
     Capitals
    -2.31
    POSITIVE LOGITS
     Jun
    8.36
    Jun
    7.42
    jun
    5.59
     Jul
    5.16
    Jul
    4.61
     jun
    4.49
     Aug
    4.41
    Aug
    4.21
    Apr
    3.96
     Apr
    3.93
    Activations Density 0.007%

    No Known Activations