© 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. 10-ATT-KK
    11. 14978
    Prev
    Next
    INDEX
    Explanations

    temporal phrases and conditions

    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
    0:0.09
    1:0.05
    2:0.03
    3:0.12
    4:0.04
    5:0.03
    6:0.04
    7:0.38
    8:0.02
    9:0.04
    10:0.03
    11:0.08
    Negative Logits
     Ventura
    -2.70
     Slater
    -2.61
     Antioch
    -2.40
    Lev
    -2.36
     Tid
    -2.35
    Lex
    -2.33
     Lex
    -2.32
    aiden
    -2.29
     Quinn
    -2.26
     Parker
    -2.25
    POSITIVE LOGITS
    Gi
    2.41
    BIP
    2.31
     GP
    2.14
    ulp
    2.13
    ェ
    2.08
    ecause
    2.05
    assetsadobe
    2.05
    rike
    2.04
    iband
    2.04
     compr
    2.02
    Activations Density 0.020%

    No Known Activations