© 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. 9978
    Prev
    Next
    INDEX
    Explanations

    expressions of concern or criticism regarding complex social issues

    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
    0:0.04
    1:0.03
    2:0.12
    3:0.12
    4:0.13
    5:0.20
    6:0.04
    7:0.05
    8:0.05
    9:0.09
    10:0.04
    11:0.05
    Negative Logits
     ­
    -4.69
    ‑
    -3.73
    )—
    -3.44
    —"
    -3.31
    ‐
    -3.05
    "—
    -3.02
    ­
    -2.96
    ],"
    -2.87
    �
    -2.86
    —
    -2.81
    POSITIVE LOGITS
     doesnt
    6.06
     dont
    5.93
     alot
    5.84
     didnt
    5.67
     lol
    5.39
     tho
    5.31
     haha
    5.22
     :(
    4.80
     wont
    4.79
     kinda
    4.73
    Activations Density 1.784%

    No Known Activations