© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 12521
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to openings and significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    1:0.26
    2:0.04
    3:0.14
    4:0.04
    5:0.02
    6:0.09
    7:0.14
    8:0.03
    9:0.03
    10:0.04
    11:0.08
    Negative Logits
    Fine
    -2.83
    Pure
    -2.77
    REDACTED
    -2.54
    Solid
    -2.31
     wearable
    -2.27
    Sharp
    -2.24
    severe
    -2.22
     coarse
    -2.20
     Raw
    -2.19
    onomous
    -2.15
    POSITIVE LOGITS
     Opening
    5.60
     opening
    5.59
    Opening
    5.02
    opening
    4.70
     closing
    4.65
     openings
    4.47
     Closing
    4.02
     opener
    3.57
     opened
    3.41
     closes
    3.32
    Activations Density 0.025%

    No Known Activations