© 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. 7789
    Prev
    Next
    INDEX
    Explanations

    punctuations and symbols, primarily focusing on context-changing marks

    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
    0:0.04
    1:0.16
    2:0.03
    3:0.04
    4:0.03
    5:0.04
    6:0.20
    7:0.04
    8:0.03
    9:0.28
    10:0.02
    11:0.04
    Negative Logits
    ォ
    -3.85
    BM
    -3.75
     Kag
    -3.63
     Mao
    -3.52
     }}
    -3.51
    ober
    -3.43
    MB
    -3.43
    amber
    -3.40
     CAL
    -3.33
     ANG
    -3.30
    POSITIVE LOGITS
     121
    6.34
    121
    6.06
     119
    6.04
    124
    5.95
     122
    5.94
     124
    5.86
    122
    5.74
     117
    5.73
     118
    5.72
     127
    5.71
    Activations Density 0.001%

    No Known Activations