© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 14822
    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
    1:0.08
    2:0.07
    3:0.07
    4:0.08
    5:0.08
    6:0.08
    7:0.09
    8:0.08
    9:0.09
    10:0.08
    11:0.07
    Negative Logits
    ictionary
    -3.56
     vomit
    -2.84
    ottest
    -2.82
     hashtag
    -2.52
     lick
    -2.49
     memes
    -2.48
     val
    -2.45
     vot
    -2.45
    otle
    -2.43
     rave
    -2.42
    POSITIVE LOGITS
     Dag
    3.57
     Dull
    2.96
     Cly
    2.82
     Matth
    2.81
     Guatemala
    2.76
     Shaw
    2.71
     Edmund
    2.70
     McCl
    2.68
     Dul
    2.63
     Faw
    2.62
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.