© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 15365
    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
    0:0.06
    1:0.08
    2:0.07
    3:0.08
    4:0.09
    5:0.08
    6:0.09
    7:0.08
    8:0.07
    9:0.08
    10:0.09
    11:0.08
    Negative Logits
     Tent
    -3.01
    omorphic
    -2.75
     cavern
    -2.65
    scl
    -2.61
     specs
    -2.60
     Saur
    -2.58
     goblins
    -2.48
     Nib
    -2.48
     Bigfoot
    -2.46
     Cumber
    -2.44
    POSITIVE LOGITS
    OTUS
    2.69
    YE
    2.67
    vae
    2.66
    xa
    2.65
    %"
    2.63
     dy
    2.58
    IU
    2.57
    uti
    2.54
    Yo
    2.53
    Ku
    2.49
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.