© 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. 8810
    Prev
    Next
    INDEX
    Explanations

    phrases expressing disappointment or struggle related to personal circumstances

    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
    1:0.03
    2:0.11
    3:0.09
    4:0.03
    5:0.06
    6:0.02
    7:0.41
    8:0.02
    9:0.01
    10:0.10
    11:0.01
    Negative Logits
    SHIP
    -2.79
    PLIED
    -2.63
    burgh
    -2.57
    gard
    -2.54
    heid
    -2.43
    veland
    -2.34
    olk
    -2.32
    DIV
    -2.31
    hai
    -2.25
    iquette
    -2.23
    POSITIVE LOGITS
     finally
    5.85
     culminated
    3.71
     culminating
    3.31
     Finally
    3.23
     eventually
    3.15
     suddenly
    3.12
     recently
    3.08
    now
    2.90
    uddenly
    2.78
    today
    2.77
    Activations Density 0.537%

    No Known Activations