© 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. 22387
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and exclamations related to frustration or urgency

    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
    1:0.09
    2:0.04
    3:0.07
    4:0.06
    5:0.04
    6:0.17
    7:0.03
    8:0.02
    9:0.09
    10:0.07
    11:0.20
    Negative Logits
    arily
    -3.19
     Ars
    -2.99
    ydia
    -2.87
    :[
    -2.80
    qqa
    -2.77
    inarily
    -2.72
    raph
    -2.70
    phthal
    -2.68
    rawler
    -2.58
    roth
    -2.53
    POSITIVE LOGITS
    ??
    5.84
    ???
    5.43
    ????
    5.13
    !!
    5.11
    !!!!
    5.01
    ??
    4.87
    ?????
    4.82
    ????????
    4.75
    !!"
    4.69
    !!
    4.63
    Activations Density 0.001%

    No Known Activations