© 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. 5-ATT-KK
    6. 28370
    Prev
    Next
    INDEX
    Explanations

    anatomical terms related to surgery and healing processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.01
    2:0.06
    3:0.05
    4:0.05
    5:0.05
    6:0.03
    7:0.04
    8:0.04
    9:0.10
    10:0.35
    11:0.14
    Negative Logits
     Meier
    -1.24
     Squadron
    -1.22
    Pand
    -1.22
    RPG
    -1.17
     Kelley
    -1.14
     nihil
    -1.14
     franchises
    -1.12
    romeda
    -1.11
    elligent
    -1.11
    ombies
    -1.11
    POSITIVE LOGITS
     protr
    1.57
     swollen
    1.57
     cavity
    1.49
     deteriorated
    1.42
     stabilized
    1.42
     circumference
    1.40
     anterior
    1.38
     swelling
    1.36
     artery
    1.36
     ridge
    1.35
    Activations Density 0.625%

    No Known Activations