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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 36946
    Prev
    Next
    INDEX
    Explanations

    references to academic journals and research publications

    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
    0:0.01
    1:0.01
    2:0.06
    3:0.08
    4:0.12
    5:0.02
    6:0.05
    7:0.30
    8:0.04
    9:0.04
    10:0.11
    11:0.11
    Negative Logits
    chers
    -1.29
     unrealistic
    -1.23
     excessive
    -1.23
     allowable
    -1.22
     submer
    -1.22
     rever
    -1.19
     dipping
    -1.18
     swallowing
    -1.17
     spitting
    -1.15
    roph
    -1.15
    POSITIVE LOGITS
     Proceedings
    1.52
    doi
    1.45
     Springer
    1.40
     journal
    1.40
    Led
    1.39
     pdf
    1.38
    papers
    1.37
     Tribune
    1.34
     annot
    1.28
     journals
    1.28
    Activations Density 0.047%

    No Known Activations