© 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. 17014
    Prev
    Next
    INDEX
    Explanations

    references to emotional or moral concepts in relation to actions or choices

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.32
    1:0.01
    2:0.10
    3:0.08
    4:0.07
    5:0.03
    6:0.04
    7:0.02
    8:0.06
    9:0.08
    10:0.08
    11:0.05
    Negative Logits
     FANTASY
    -1.80
     shudder
    -1.72
     wont
    -1.69
     archived
    -1.68
     fibre
    -1.67
     resumes
    -1.66
     certific
    -1.60
     compan
    -1.56
     foregoing
    -1.56
     populace
    -1.55
    POSITIVE LOGITS
    iq
    1.87
    iddler
    1.84
    adr
    1.84
    atinum
    1.71
    zie
    1.70
    Ring
    1.66
    forcer
    1.65
    zin
    1.64
    Interstitial
    1.61
     —
    1.60
    Activations Density 0.151%

    No Known Activations