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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14786
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    1:0.07
    2:0.08
    3:0.08
    4:0.09
    5:0.08
    6:0.08
    7:0.07
    8:0.08
    9:0.09
    10:0.07
    11:0.08
    Negative Logits
     PsyNet
    -3.02
     CARD
    -2.90
     Prel
    -2.83
     Temper
    -2.75
     redress
    -2.52
     Empires
    -2.51
    hift
    -2.48
     Pagan
    -2.39
     Soc
    -2.39
    �
    -2.35
    POSITIVE LOGITS
    pee
    2.78
    essen
    2.52
    artments
    2.51
    ester
    2.51
     gestation
    2.43
    hari
    2.35
    aining
    2.32
    ociated
    2.31
    lished
    2.29
     raspberry
    2.27
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.