© 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. 22453
    Prev
    Next
    INDEX
    Explanations

    narrative components related to events, actions, and physical descriptions

    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
    0:0.07
    1:0.05
    2:0.09
    3:0.26
    4:0.03
    5:0.01
    6:0.07
    7:0.10
    8:0.04
    9:0.04
    10:0.17
    11:0.03
    Negative Logits
    akespe
    -2.77
    —-
    -2.70
    ♦
    -2.63
    alam
    -2.40
    Cub
    -2.40
    renheit
    -2.39
    �
    -2.35
    "—
    -2.28
     Bahrain
    -2.26
    ,—
    -2.25
    POSITIVE LOGITS
     Jan
    8.47
    Jan
    7.52
     Feb
    6.08
     Nov
    5.67
     Jul
    5.44
     Aug
    5.19
     Oct
    5.15
     Dec
    5.12
    Nov
    5.05
    Feb
    5.04
    Activations Density 0.011%

    No Known Activations