© 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. 2-ATT-KK
    11. 21305
    Prev
    Next
    INDEX
    Explanations

    references to measurements, particularly length and distance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    2:0.14
    3:0.06
    4:0.14
    5:0.14
    6:0.02
    7:0.03
    8:0.06
    9:0.19
    10:0.06
    11:0.02
    Negative Logits
    ulner
    -1.43
    lists
    -1.41
     Skies
    -1.31
     Epidem
    -1.30
     Ens
    -1.26
    quest
    -1.23
    hess
    -1.23
    Nation
    -1.22
    xit
    -1.21
     acad
    -1.21
    POSITIVE LOGITS
     diameter
    1.66
     paddle
    1.38
     protr
    1.35
     horizontally
    1.34
     circumference
    1.28
     shaved
    1.27
     needles
    1.25
     width
    1.25
     lateral
    1.24
     gorilla
    1.23
    Activations Density 0.014%

    No Known Activations