© 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. 9-ATT-KK
    11. 20526
    Prev
    Next
    INDEX
    Explanations

    pronouns or references to individuals involved in a situation

    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
    0:0.09
    1:0.09
    2:0.08
    3:0.08
    4:0.08
    5:0.07
    6:0.07
    7:0.07
    8:0.07
    9:0.09
    10:0.08
    11:0.07
    Negative Logits
     weakest
    -2.82
     overs
    -2.73
     imagination
    -2.54
     Influ
    -2.41
    rows
    -2.40
    ruciating
    -2.34
     averages
    -2.32
     unintentional
    -2.32
     simplest
    -2.29
     Rout
    -2.28
    POSITIVE LOGITS
    aya
    3.43
    celona
    3.38
     Catalan
    3.30
    atel
    3.13
     Madrid
    3.07
    Putin
    3.01
    Tok
    2.94
     Kara
    2.88
    uku
    2.85
     Sev
    2.84
    Activations Density 0.000%

    No Known Activations