© 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. 9-ATT-KK
    11. 3918
    Prev
    Next
    INDEX
    Explanations

    instances of legal and political references

    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
    0:0.09
    1:0.02
    2:0.04
    3:0.03
    4:0.05
    5:0.03
    6:0.24
    7:0.05
    8:0.07
    9:0.27
    10:0.02
    11:0.04
    Negative Logits
     flu
    -4.16
     Haitian
    -4.07
     Marse
    -3.98
     Hait
    -3.92
    ンジ
    -3.72
    namese
    -3.70
     Flu
    -3.64
     Spell
    -3.61
     CFL
    -3.58
    ��
    -3.55
    POSITIVE LOGITS
     Roberts
    11.91
    Roberts
    11.35
     Robertson
    6.20
     Rogue
    4.54
    Rog
    4.40
     Rogers
    4.32
     Robbins
    4.31
     Rip
    4.30
    Rogue
    4.27
    KS
    4.25
    Activations Density 0.008%

    No Known Activations