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

    Neuronpedia

    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. 19905
    Prev
    Next
    INDEX
    Explanations

    sentiments regarding career decisions and future aspirations

    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
    1:0.03
    2:0.17
    3:0.21
    4:0.05
    5:0.11
    6:0.03
    7:0.11
    8:0.06
    9:0.03
    10:0.09
    11:0.02
    Negative Logits
    ��
    -2.56
    ��
    -2.48
    Response
    -2.35
    warning
    -2.25
    livious
    -2.20
     eyewitness
    -2.20
    yip
    -2.12
    Witness
    -2.10
     unint
    -2.05
     eleph
    -2.03
    POSITIVE LOGITS
     my
    3.12
     career
    2.83
     myself
    2.83
     championships
    2.76
     careers
    2.75
     retirement
    2.64
     competition
    2.62
     offseason
    2.60
     workouts
    2.59
     season
    2.52
    Activations Density 0.459%

    No Known Activations