© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 2025
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to a specific individual, Chris Stone, and their activities or characteristics

    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
    2:0.05
    3:0.02
    4:0.05
    5:0.02
    6:0.38
    7:0.03
    8:0.05
    9:0.19
    10:0.02
    11:0.04
    Negative Logits
    ollah
    -4.09
     NCT
    -4.08
    accompan
    -4.02
    bilt
    -3.56
     monop
    -3.55
     nodd
    -3.46
     Hik
    -3.36
    LG
    -3.33
     nurs
    -3.31
     AAC
    -3.31
    POSITIVE LOGITS
     Stone
    11.60
    Stone
    10.90
     Stones
    9.05
     stone
    8.97
     stones
    8.82
    stones
    7.18
    stone
    6.80
     rocks
    5.34
    estone
    5.13
    estones
    4.90
    Activations Density 0.012%

    No Known Activations