© 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. 6941
    Prev
    Next
    INDEX
    Explanations

    negation and phrases indicating recovery or assistance

    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
    1:0.04
    2:0.13
    3:0.06
    4:0.03
    5:0.04
    6:0.20
    7:0.04
    8:0.04
    9:0.24
    10:0.04
    11:0.03
    Negative Logits
     Planes
    -3.68
     pigeon
    -3.67
     Cree
    -3.57
    Pak
    -3.56
     Gates
    -3.52
     Seat
    -3.50
     Nig
    -3.45
     Fletcher
    -3.34
     Pew
    -3.33
     Pamela
    -3.32
    POSITIVE LOGITS
     recovery
    7.99
     Recovery
    7.94
     recover
    6.94
     Recover
    6.89
     recovers
    6.77
    overy
    6.50
     recovered
    6.18
     recovering
    6.05
     healing
    4.40
     Healing
    4.29
    Activations Density 0.001%

    No Known Activations