© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 6304
    Prev
    Next
    INDEX
    Explanations

    phrases related to sharing experiences and support within communities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.07
    1:0.05
    2:0.07
    3:0.16
    4:0.04
    5:0.11
    6:0.04
    7:0.05
    8:0.04
    9:0.05
    10:0.04
    11:0.23
    Negative Logits
     (−
    -2.50
     ('
    -2.46
    *,
    -2.33
     Scarlet
    -2.31
     Crimson
    -2.30
    *:
    -2.30
     Fault
    -2.29
     Frazier
    -2.29
    ',"
    -2.26
     antibodies
    -2.25
    POSITIVE LOGITS
    ventures
    3.41
    advertising
    3.20
    venture
    3.13
     #
    3.09
    gaming
    2.98
    ategory
    2.87
    famous
    2.83
    loe
    2.80
    online
    2.76
    walker
    2.73
    Activations Density 0.004%

    No Known Activations