© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 21918
    Prev
    Next
    INDEX
    Explanations

    references to children and their experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.04
    2:0.15
    3:0.04
    4:0.07
    5:0.10
    6:0.03
    7:0.04
    8:0.03
    9:0.28
    10:0.07
    11:0.03
    Negative Logits
    arth
    -1.38
    irmation
    -1.35
    ropolitan
    -1.34
     precedent
    -1.27
    berus
    -1.27
     hypothesis
    -1.26
     derog
    -1.25
     mantle
    -1.23
     arbit
    -1.23
    エ
    -1.23
    POSITIVE LOGITS
     Byron
    1.37
     addicted
    1.33
     diabetic
    1.31
     diapers
    1.31
     epile
    1.28
     Doodle
    1.28
     Sick
    1.28
     epilepsy
    1.27
     Moe
    1.26
     leukemia
    1.23
    Activations Density 0.037%

    No Known Activations