© 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. 10-ATT-KK
    11. 6754
    Prev
    Next
    INDEX
    Explanations

    phrases related to subscribing or accessing information

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.04
    3:0.05
    4:0.22
    5:0.06
    6:0.03
    7:0.04
    8:0.30
    9:0.06
    10:0.04
    11:0.04
    Negative Logits
    …)
    -3.09
    ••
    -3.05
    ..
    -2.92
    ..."
    -2.84
     –
    -2.74
     »
    -2.71
     …
    -2.68
    ….
    -2.61
    …..
    -2.59
     >>>
    -2.52
    POSITIVE LOGITS
    ombs
    2.25
    abus
    2.06
     Balt
    2.05
    taboola
    2.04
    ���
    1.98
     adjud
    1.97
    lah
    1.94
     Broadcasting
    1.94
     Hilbert
    1.89
     costs
    1.89
    Activations Density 0.001%

    No Known Activations