© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 13032
    Prev
    Next
    INDEX
    Explanations

    statements related to decision-making and concerns about job security in a coaching context

    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
    0:0.06
    1:0.02
    2:0.06
    3:0.03
    4:0.04
    5:0.04
    6:0.27
    7:0.04
    8:0.06
    9:0.30
    10:0.02
    11:0.02
    Negative Logits
    hu
    -3.80
    ••••
    -3.71
    hound
    -3.63
     tether
    -3.62
     welf
    -3.57
    ihu
    -3.52
     Nept
    -3.48
     harbor
    -3.44
     hemor
    -3.42
     magnet
    -3.42
    POSITIVE LOGITS
     Brooks
    11.38
    Bro
    7.34
     Brooke
    5.16
     Douglas
    4.86
     Bro
    4.68
     Bates
    4.64
     Rogers
    4.62
    oks
    4.44
    brook
    4.42
     Roberts
    4.38
    Activations Density 0.004%

    No Known Activations