© 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. 20547
    Prev
    Next
    INDEX
    Explanations

    the use of the first-person pronoun "I" and references to the speaker's personal experiences or actions

    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
    0:0.07
    1:0.23
    2:0.08
    3:0.06
    4:0.03
    5:0.03
    6:0.10
    7:0.03
    8:0.02
    9:0.23
    10:0.05
    11:0.02
    Negative Logits
     slideshow
    -3.07
     Pillar
    -3.04
     Spect
    -2.89
    iage
    -2.86
    Sad
    -2.85
     Perse
    -2.81
    265
    -2.79
     Sad
    -2.74
     Opposition
    -2.73
     Apex
    -2.71
    POSITIVE LOGITS
    know
    5.50
     knows
    5.10
    Know
    5.03
     know
    4.93
     knew
    4.91
     Know
    4.88
     knowing
    4.57
     KNOW
    4.24
     known
    3.76
     knowledge
    3.74
    Activations Density 0.022%

    No Known Activations