© 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. 10-ATT-KK
    11. 8000
    Prev
    Next
    INDEX
    Explanations

    elements related to structured argumentation or a list format in discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.03
    2:0.11
    3:0.07
    4:0.06
    5:0.17
    6:0.03
    7:0.08
    8:0.04
    9:0.22
    10:0.03
    11:0.09
    Negative Logits
     even
    -2.69
     meanwhile
    -2.60
     bother
    -2.39
     indeed
    -2.39
    .」
    -2.37
     moreover
    -2.29
    arta
    -2.23
     likewise
    -2.21
     otherwise
    -2.19
     similarly
    -2.16
    POSITIVE LOGITS
    *:
    3.24
    %:
    2.96
    ):
    2.94
    Firstly
    2.86
    First
    2.61
    Story
    2.58
    :-
    2.56
    ]:
    2.55
    Every
    2.54
     Winners
    2.53
    Activations Density 0.075%

    No Known Activations