© 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. 10922
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional distress and support

    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
    0:0.08
    1:0.02
    2:0.43
    3:0.12
    4:0.03
    5:0.08
    6:0.02
    7:0.05
    8:0.03
    9:0.03
    10:0.05
    11:0.02
    Negative Logits
    eligible
    -2.95
     Scholarship
    -2.69
     eligibility
    -2.66
     scholarships
    -2.64
     reuse
    -2.62
    pedia
    -2.59
    profits
    -2.54
    winner
    -2.52
     specialization
    -2.51
     Foss
    -2.48
    POSITIVE LOGITS
     Anxiety
    5.07
     panic
    4.78
     anxiety
    4.76
     calmed
    4.57
     emotion
    4.45
     emotions
    4.44
    xiety
    4.44
     calm
    4.43
     feeling
    4.42
     sadness
    4.37
    Activations Density 1.022%

    No Known Activations