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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 14027
    Prev
    Next
    INDEX
    Explanations

    questions or inquiries about future events or expectations

    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
    0:0.05
    1:0.04
    2:0.11
    3:0.10
    4:0.10
    5:0.06
    6:0.03
    7:0.15
    8:0.13
    9:0.07
    10:0.05
    11:0.05
    Negative Logits
    】
    -2.37
     �
    -2.29
     […]
    -2.27
     ¶
    -2.25
    wal
    -2.21
    ".[
    -2.06
     decre
    -2.05
     [*
    -2.04
    ***
    -2.04
     Tsu
    -2.04
    POSITIVE LOGITS
    Interstitial
    2.39
    ricular
    2.35
    ?:
    2.30
    ?
    2.28
    rome
    2.25
    nesium
    2.19
    roman
    2.18
    .?
    2.16
    ?
    2.14
    rame
    2.14
    Activations Density 0.003%

    No Known Activations