© 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. 4028
    Prev
    Next
    INDEX
    Explanations

    expressions of opinion and emotional reactions

    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
    0:0.06
    1:0.02
    2:0.05
    3:0.27
    4:0.02
    5:0.09
    6:0.02
    7:0.05
    8:0.02
    9:0.02
    10:0.32
    11:0.01
    Negative Logits
     unrestricted
    -2.07
     unchecked
    -2.00
     Worldwide
    -1.99
    OURCE
    -1.94
     uncertainties
    -1.90
     DOI
    -1.86
     unregulated
    -1.86
    Increases
    -1.80
    "></
    -1.79
     datasets
    -1.78
    POSITIVE LOGITS
     nice
    2.45
     gimmick
    2.41
     funny
    2.34
     classy
    2.31
     amusing
    2.27
     alright
    2.25
     cute
    2.24
     neat
    2.22
     lovely
    2.18
     witty
    2.16
    Activations Density 0.174%

    No Known Activations