© 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. 7083
    Prev
    Next
    INDEX
    Explanations

    punctuation and sentence structures that convey finality or conclusions

    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
    0:0.07
    1:0.03
    2:0.07
    3:0.03
    4:0.04
    5:0.03
    6:0.28
    7:0.03
    8:0.09
    9:0.23
    10:0.01
    11:0.03
    Negative Logits
    覚醒
    -4.16
     Tuls
    -4.01
    �
    -3.94
    catentry
    -3.73
     butterfly
    -3.72
    haw
    -3.69
     Hawks
    -3.60
     owl
    -3.56
    apult
    -3.52
     holog
    -3.51
    POSITIVE LOGITS
     Sin
    10.94
    Sin
    10.39
    sin
    8.05
     sin
    7.76
     Sins
    6.65
     Sinclair
    5.71
     sinful
    5.58
     Sass
    5.58
     sins
    4.82
     sinners
    4.38
    Activations Density 0.002%

    No Known Activations