© 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. 36190
    Prev
    Next
    INDEX
    Explanations

    statements related to authority or oversight roles

    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
    1:0.01
    2:0.18
    3:0.19
    4:0.13
    5:0.06
    6:0.04
    7:0.04
    8:0.05
    9:0.10
    10:0.08
    11:0.04
    Negative Logits
     Instr
    -1.41
     meanwhile
    -1.28
     streng
    -1.26
    lyak
    -1.26
     conclud
    -1.23
    ADRA
    -1.20
    ADVERTISEMENT
    -1.17
    VERTISEMENT
    -1.15
     advis
    -1.12
    izoph
    -1.12
    POSITIVE LOGITS
    origin
    1.19
    changed
    1.17
    Definition
    1.15
     Inher
    1.14
    /(
    1.11
    escape
    1.09
    access
    1.08
     Contains
    1.06
    complete
    1.06
    dependent
    1.04
    Activations Density 0.540%

    No Known Activations