© 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. 3-ATT-KK
    11. 5576
    Prev
    Next
    INDEX
    Explanations

    preferences and opinions regarding political options or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.03
    2:0.11
    3:0.08
    4:0.02
    5:0.03
    6:0.04
    7:0.09
    8:0.23
    9:0.07
    10:0.05
    11:0.17
    Negative Logits
     seism
    -1.16
     epidemic
    -1.10
    azeera
    -1.09
     legion
    -1.00
     counting
    -1.00
    pires
    -0.99
    illion
    -0.98
     tallied
    -0.98
     outbreak
    -0.95
     precincts
    -0.94
    POSITIVE LOGITS
    aline
    1.24
    ahime
    1.22
    than
    1.14
    anything
    1.12
    inen
    1.09
     XD
    1.06
    anism
    1.04
    Anything
    1.01
    hent
    1.01
    luaj
    1.01
    Activations Density 0.013%

    No Known Activations