© 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. 17260
    Prev
    Next
    INDEX
    Explanations

    negative sentiments toward various situations and topics

    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
    0:0.05
    1:0.17
    2:0.11
    3:0.05
    4:0.08
    5:0.09
    6:0.05
    7:0.17
    8:0.04
    9:0.06
    10:0.03
    11:0.07
    Negative Logits
     Cot
    -2.90
     Lange
    -2.67
     Greenwood
    -2.59
    orney
    -2.40
     stub
    -2.24
     Wy
    -2.24
    endor
    -2.18
     Bunker
    -2.16
    Nich
    -2.16
     Bart
    -2.13
    POSITIVE LOGITS
     okay
    3.94
     OK
    3.60
     alright
    3.38
     ok
    3.31
     Okay
    3.11
    Okay
    3.07
    Fine
    2.91
     Alright
    2.81
     fine
    2.78
    nah
    2.64
    Activations Density 0.007%

    No Known Activations