© 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. 8054
    Prev
    Next
    INDEX
    Explanations

    narratives about personal physical experiences, particularly those involving distress or bodily 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
    0:0.09
    1:0.03
    2:0.16
    3:0.18
    4:0.07
    5:0.12
    6:0.03
    7:0.12
    8:0.03
    9:0.02
    10:0.05
    11:0.05
    Negative Logits
     Partnership
    -2.04
     Diversity
    -2.04
    actionDate
    -2.03
     Educ
    -2.02
    rentices
    -2.01
     Vanguard
    -1.99
     Topics
    -1.98
     borrower
    -1.94
     Architects
    -1.93
     hires
    -1.90
    POSITIVE LOGITS
     nausea
    2.97
     nause
    2.88
     sweating
    2.84
     my
    2.82
     coughing
    2.80
     vomiting
    2.76
     throb
    2.75
     smelled
    2.70
     uncontroll
    2.67
     clen
    2.67
    Activations Density 0.502%

    No Known Activations