© 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. 5-ATT-KK
    11. 35650
    Prev
    Next
    INDEX
    Explanations

    phrases that express emphasis or negativity regarding the subject matter

    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
    0:0.02
    1:0.03
    2:0.11
    3:0.16
    4:0.07
    5:0.04
    6:0.23
    7:0.05
    8:0.03
    9:0.04
    10:0.09
    11:0.08
    Negative Logits
     challeng
    -1.71
    kefeller
    -1.59
    issance
    -1.51
    interstitial
    -1.47
     endeavour
    -1.39
     someday
    -1.34
     Archdemon
    -1.30
    phrine
    -1.29
    ''.
    -1.29
    ihilation
    -1.28
    POSITIVE LOGITS
    etting
    1.31
     Contracts
    1.30
     damning
    1.30
    yet
    1.29
    フォ
    1.27
     Gibson
    1.26
    ording
    1.25
     Words
    1.23
    ince
    1.22
     Architects
    1.21
    Activations Density 0.022%

    No Known Activations