© 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. 23282
    Prev
    Next
    INDEX
    Explanations

    negative descriptors and criticisms related to actions and statements

    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
    0:0.03
    1:0.07
    2:0.03
    3:0.04
    4:0.32
    5:0.04
    6:0.04
    7:0.15
    8:0.02
    9:0.09
    10:0.03
    11:0.10
    Negative Logits
    toggle
    -3.44
    accompan
    -2.99
    raits
    -2.90
    "},{"
    -2.83
    merga
    -2.79
     GOODMAN
    -2.66
    estones
    -2.63
    Enlarge
    -2.55
    vantage
    -2.45
    ィ
    -2.42
    POSITIVE LOGITS
     misguided
    5.13
     incompetence
    4.98
     incompetent
    4.98
     stupidity
    4.89
     ignorant
    4.86
     incompet
    4.84
     disingen
    4.80
     grossly
    4.74
     foolish
    4.72
     stupid
    4.65
    Activations Density 0.470%

    No Known Activations