© 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. 6307
    Prev
    Next
    INDEX
    Explanations

    references to specific arguments and conditions regarding regulations or limitations

    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
    0:0.03
    1:0.15
    2:0.06
    3:0.08
    4:0.08
    5:0.05
    6:0.05
    7:0.08
    8:0.03
    9:0.18
    10:0.11
    11:0.05
    Negative Logits
     brackets
    -2.34
     acc
    -2.33
     rec
    -2.30
     reciproc
    -2.24
     fac
    -2.21
     happens
    -2.18
     sort
    -2.16
    ã
    -2.12
    aley
    -2.11
     invites
    -2.09
    POSITIVE LOGITS
    netflix
    3.20
     OPEC
    3.06
    drm
    2.75
    iker
    2.69
     Wis
    2.66
     Wenger
    2.58
     Tank
    2.58
    iw
    2.51
    BuyableInstoreAndOnline
    2.51
     Wak
    2.43
    Activations Density 0.002%

    No Known Activations