© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 19707
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the significance of specific facts or assertions

    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
    0:0.03
    1:0.02
    2:0.07
    3:0.19
    4:0.10
    5:0.06
    6:0.08
    7:0.10
    8:0.06
    9:0.06
    10:0.06
    11:0.13
    Negative Logits
    ''.
    -1.57
     Fenrir
    -1.49
    '.
    -1.45
    `.
    -1.44
    .</
    -1.44
    ').
    -1.41
     Brist
    -1.34
    .''.
    -1.31
    ̶
    -1.31
     �
    -1.28
    POSITIVE LOGITS
     speaks
    1.21
     sanitation
    1.20
     Collective
    1.18
     reflects
    1.14
     curfew
    1.14
     linkage
    1.11
    EVA
    1.11
    artments
    1.11
     ensures
    1.10
     society
    1.10
    Activations Density 0.006%

    No Known Activations