© 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. 11048
    Prev
    Next
    INDEX
    Explanations

    negations and expressions of uncertainty or lack of control

    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
    0:0.02
    1:0.05
    2:0.03
    3:0.05
    4:0.03
    5:0.03
    6:0.31
    7:0.03
    8:0.02
    9:0.06
    10:0.06
    11:0.26
    Negative Logits
     Nelson
    -2.86
     Moons
    -2.74
    wine
    -2.74
     Kaine
    -2.72
     Stone
    -2.69
     Forth
    -2.62
     Richmond
    -2.60
     Strange
    -2.60
    ,)
    -2.59
    imp
    -2.59
    POSITIVE LOGITS
    �
    4.52
    ¨
    3.58
    »
    3.52
    �
    3.25
    ´
    3.20
    cffffcc
    3.20
    ?」
    3.19
    」
    3.18
    ・
    3.09
    ּ
    3.02
    Activations Density 0.292%

    No Known Activations