© 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 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. 8564
    Prev
    Next
    INDEX
    Explanations

    expressions of positive emotions related to experiences and achievements

    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
    2:0.18
    3:0.18
    4:0.05
    5:0.11
    6:0.02
    7:0.09
    8:0.05
    9:0.02
    10:0.13
    11:0.01
    Negative Logits
    Solution
    -2.71
    pmwiki
    -2.57
    Topic
    -2.53
     delinquent
    -2.50
    Recommend
    -2.47
     Suggest
    -2.45
    opathy
    -2.38
    opath
    -2.37
    ��
    -2.32
    Dialog
    -2.31
    POSITIVE LOGITS
     congratulations
    3.59
     thrilled
    3.56
     exhilar
    3.55
     amazing
    3.33
     excitement
    3.32
    Congratulations
    3.25
     Congratulations
    3.24
     congr
    3.21
     incredible
    3.20
     unbelievable
    3.17
    Activations Density 0.511%

    No Known Activations