© 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. 9-ATT-KK
    11. 17751
    Prev
    Next
    INDEX
    Explanations

    elements related to character development and the emotional impact of narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.01
    2:0.05
    3:0.16
    4:0.02
    5:0.07
    6:0.02
    7:0.06
    8:0.03
    9:0.02
    10:0.42
    11:0.05
    Negative Logits
    same
    -2.26
     awaiting
    -2.25
     equivalents
    -2.17
     tomorrow
    -2.12
    currently
    -2.11
     SHALL
    -2.10
     nearest
    -2.06
    leground
    -2.04
    expected
    -2.03
     await
    -2.03
    POSITIVE LOGITS
     inception
    2.53
     1969
    2.29
     unforgettable
    2.15
     pioneering
    2.14
     1977
    2.14
     1981
    2.14
     founding
    2.14
     1947
    2.13
     1978
    2.12
     memorable
    2.11
    Activations Density 0.625%

    No Known Activations