© 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. 2-ATT-KK
    6. 23003
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    0:0.08
    1:0.07
    2:0.09
    3:0.08
    4:0.08
    5:0.09
    6:0.08
    7:0.06
    8:0.07
    9:0.08
    10:0.07
    11:0.09
    Negative Logits
    Thumbnail
    -1.59
    UFC
    -1.37
    Clar
    -1.36
    Dex
    -1.32
    Vi
    -1.27
     HK
    -1.27
     KL
    -1.26
    WER
    -1.26
    oto
    -1.25
    Line
    -1.25
    POSITIVE LOGITS
    agascar
    1.28
    iculture
    1.28
    pport
    1.27
     proced
    1.25
    itiveness
    1.22
     advers
    1.22
     Presbyterian
    1.21
     pastoral
    1.21
     solicit
    1.21
     mascul
    1.19
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.