© 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. 240
    Prev
    Next
    INDEX
    Explanations

    references to laws and legal implications involving public disturbances or misconduct

    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
    0:0.08
    1:0.03
    2:0.25
    3:0.15
    4:0.05
    5:0.10
    6:0.03
    7:0.07
    8:0.07
    9:0.03
    10:0.07
    11:0.02
    Negative Logits
    luster
    -2.73
    ォ
    -2.56
     Catalyst
    -2.47
     FANT
    -2.33
     Hatt
    -2.28
     Aub
    -2.19
     Sequ
    -2.17
     dwindling
    -2.16
    earchers
    -2.16
     layoffs
    -2.14
    POSITIVE LOGITS
     punishable
    4.81
     unlawful
    4.53
    criminal
    4.51
     legal
    4.49
     criminal
    4.46
     legality
    4.46
    riminal
    4.41
     illegal
    4.38
     prosecution
    4.35
     lawful
    4.32
    Activations Density 0.538%

    No Known Activations