© 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. 14657
    Prev
    Next
    INDEX
    Explanations

    structures indicating comparisons or contrasts

    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
    0:0.05
    1:0.02
    2:0.07
    3:0.27
    4:0.03
    5:0.05
    6:0.04
    7:0.04
    8:0.03
    9:0.03
    10:0.18
    11:0.13
    Negative Logits
    ients
    -2.34
     colleagues
    -2.29
    iaries
    -2.28
    doms
    -2.00
     sustained
    -1.98
     enterprises
    -1.96
     wills
    -1.93
     engagements
    -1.86
    verages
    -1.86
     clients
    -1.85
    POSITIVE LOGITS
    ̶
    3.32
    �
    3.28
    ————
    3.06
    �
    3.04
    </
    3.01
    [/
    2.97
    �
    2.83
    �
    2.81
    ****
    2.81
    ====
    2.69
    Activations Density 0.098%

    No Known Activations