© 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. 910
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions and their associated affiliations

    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
    0:0.05
    1:0.34
    2:0.03
    3:0.05
    4:0.06
    5:0.17
    6:0.04
    7:0.05
    8:0.04
    9:0.03
    10:0.04
    11:0.05
    Negative Logits
     still
    -3.35
    still
    -2.78
     Cancel
    -2.77
     okay
    -2.63
    no
    -2.56
    sure
    -2.48
     leftover
    -2.45
     maybe
    -2.44
     meanwhile
    -2.44
     probably
    -2.42
    POSITIVE LOGITS
     First
    2.97
    GP
    2.72
    First
    2.61
    ensable
    2.58
    ipt
    2.56
    FIR
    2.56
    ental
    2.56
    Firstly
    2.54
    obs
    2.52
    FER
    2.48
    Activations Density 0.008%

    No Known Activations