© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14790
    Prev
    Next
    INDEX
    Explanations

    concepts related to healing and recovery processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.18
    1:0.09
    2:0.04
    3:0.06
    4:0.10
    5:0.02
    6:0.03
    7:0.17
    8:0.03
    9:0.04
    10:0.08
    11:0.08
    Negative Logits
     Fut
    -2.78
     Burger
    -2.73
     Dick
    -2.60
    Dick
    -2.56
     Shelby
    -2.55
     Dunk
    -2.52
     Cheney
    -2.38
     Penguin
    -2.34
     Crawford
    -2.27
     Inferno
    -2.26
    POSITIVE LOGITS
     healing
    4.97
     heal
    4.93
     Healing
    4.42
     healed
    4.41
     healer
    4.31
     heals
    4.09
     Heal
    4.03
     Healer
    3.93
     shaman
    3.37
     regener
    3.17
    Activations Density 0.008%

    No Known Activations