© 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. 10513
    Prev
    Next
    INDEX
    Explanations

    relationships and discussions around morality and religion

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.16
    2:0.18
    3:0.05
    4:0.04
    5:0.02
    6:0.07
    7:0.07
    8:0.03
    9:0.06
    10:0.13
    11:0.05
    Negative Logits
    ernel
    -3.32
    nder
    -3.16
    inson
    -2.96
    olin
    -2.88
    erva
    -2.85
     disag
    -2.85
    ternity
    -2.83
    uca
    -2.82
    culus
    -2.80
    uld
    -2.79
    POSITIVE LOGITS
     Hit
    7.99
    Hit
    6.28
     Shot
    5.31
     HIT
    5.25
     Hits
    4.63
     Hitch
    4.39
    Shot
    4.38
     Hat
    4.34
    hit
    4.12
     Lit
    4.04
    Activations Density 0.005%

    No Known Activations