© 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. 5-ATT-KK
    11. 39499
    Prev
    Next
    INDEX
    Explanations

    opinions and attitudes reflected in survey data

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.05
    3:0.08
    4:0.04
    5:0.06
    6:0.02
    7:0.03
    8:0.07
    9:0.07
    10:0.42
    11:0.06
    Negative Logits
    RIP
    -2.16
     Designed
    -2.12
     merc
    -2.10
     miracles
    -2.01
    Thumbnail
    -2.01
     buggy
    -1.96
     antiquity
    -1.93
     ransom
    -1.92
    Constructed
    -1.92
     repairs
    -1.90
    POSITIVE LOGITS
    ecided
    2.74
    ussen
    2.47
     Votes
    2.38
    irtual
    2.35
    uggest
    2.33
    atalie
    2.26
    votes
    2.22
    yden
    2.20
    Russ
    2.20
     vote
    2.14
    Activations Density 0.048%

    No Known Activations