© 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. 13930
    Prev
    Next
    INDEX
    Explanations

    phrases indicating patient removal or withdrawal situations

    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
    0:0.07
    1:0.05
    2:0.13
    3:0.05
    4:0.03
    5:0.03
    6:0.15
    7:0.04
    8:0.02
    9:0.32
    10:0.04
    11:0.02
    Negative Logits
     Spin
    -3.80
     Dream
    -3.46
     spins
    -3.43
     Biden
    -3.31
     spin
    -3.24
     SIG
    -3.22
    �
    -3.17
     Spac
    -3.17
    span
    -3.16
     Cohn
    -3.12
    POSITIVE LOGITS
     removal
    5.65
     removed
    5.58
     Removal
    5.25
     removing
    5.24
    Remove
    5.12
     extracts
    4.89
     extracted
    4.87
     remove
    4.79
     extract
    4.74
     extracting
    4.63
    Activations Density 0.005%

    No Known Activations