© 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. 6499
    Prev
    Next
    INDEX
    Explanations

    elements related to personal experiences and opinions

    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
    0:0.02
    1:0.02
    2:0.03
    3:0.04
    4:0.05
    5:0.56
    6:0.02
    7:0.03
    8:0.02
    9:0.12
    10:0.01
    11:0.03
    Negative Logits
     can
    -2.86
    Can
    -2.83
     Can
    -2.70
    sometimes
    -2.55
    thens
    -2.45
     Possible
    -2.40
     varies
    -2.38
     reacts
    -2.32
    pires
    -2.31
     predicts
    -2.29
    POSITIVE LOGITS
     instead
    8.38
     rather
    7.64
    instead
    7.14
    rather
    6.44
    Instead
    6.34
     Instead
    5.80
    Rather
    5.32
     Rather
    5.04
     anyways
    4.80
     anyway
    4.69
    Activations Density 1.163%

    No Known Activations