© 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. 21451
    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
    0:0.09
    1:0.06
    2:0.09
    3:0.07
    4:0.07
    5:0.09
    6:0.07
    7:0.05
    8:0.09
    9:0.11
    10:0.12
    11:0.05
    Negative Logits
     slightest
    -1.21
    lag
    -1.20
     landslide
    -1.18
    major
    -1.15
     coma
    -1.13
    icipated
    -1.12
     typo
    -1.11
     urgency
    -1.10
     traitor
    -1.09
     truce
    -1.03
    POSITIVE LOGITS
    ��
    1.35
     planners
    1.27
     outfits
    1.21
     broch
    1.20
     desks
    1.20
     seminars
    1.16
     chairs
    1.15
     Estate
    1.12
    knit
    1.10
    omy
    1.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.