© 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. 9-ATT-KK
    11. 5495
    Prev
    Next
    INDEX
    Explanations

    instances of dismissal or termination in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.16
    1:0.01
    2:0.08
    3:0.16
    4:0.02
    5:0.06
    6:0.02
    7:0.05
    8:0.03
    9:0.02
    10:0.31
    11:0.02
    Negative Logits
     captivity
    -2.06
     lived
    -2.03
    000000
    -2.01
     Survive
    -2.00
     existence
    -2.00
     purity
    -1.95
     treaties
    -1.93
     submission
    -1.92
     lives
    -1.91
    oneliness
    -1.90
    POSITIVE LOGITS
     fired
    2.75
    fired
    2.54
     sergeant
    2.42
     showc
    2.37
     testers
    2.34
    umbn
    2.31
     sacked
    2.25
     relieved
    2.15
    alion
    2.14
     supervisors
    2.13
    Activations Density 0.007%

    No Known Activations