© 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. 21364
    Prev
    Next
    INDEX
    Explanations

    the presence of phrases or structures that imply 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
    0:0.14
    1:0.10
    2:0.09
    3:0.05
    4:0.03
    5:0.06
    6:0.12
    7:0.03
    8:0.02
    9:0.25
    10:0.04
    11:0.02
    Negative Logits
    claw
    -3.10
    zos
    -3.03
    AIDS
    -3.01
    Zen
    -2.94
     Ort
    -2.90
    Tang
    -2.86
    YP
    -2.85
     orphans
    -2.81
    atra
    -2.80
    areth
    -2.78
    POSITIVE LOGITS
     describe
    5.92
     description
    5.84
     descriptions
    5.66
     describ
    5.62
     describing
    5.33
    desc
    5.05
     Desc
    5.03
     describes
    4.99
    Desc
    4.99
     descriptive
    4.81
    Activations Density 0.005%

    No Known Activations