© 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. 43128
    Prev
    Next
    INDEX
    Explanations

    phrases that express consideration or attention to context or perspective

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.03
    1:0.01
    2:0.22
    3:0.09
    4:0.11
    5:0.03
    6:0.05
    7:0.17
    8:0.04
    9:0.05
    10:0.09
    11:0.06
    Negative Logits
    �
    -1.60
     tolerate
    -1.53
     disliked
    -1.49
     originate
    -1.47
     specialize
    -1.40
     relate
    -1.38
    thumbnails
    -1.35
    ussian
    -1.34
    oat
    -1.34
    aku
    -1.29
    POSITIVE LOGITS
     Stead
    1.61
     hindsight
    1.53
     stead
    1.46
     immedi
    1.44
     vantage
    1.44
     backdrop
    1.42
    ilst
    1.39
    wind
    1.35
    �
    1.35
     discretion
    1.35
    Activations Density 0.002%

    No Known Activations