© 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. 22627
    Prev
    Next
    INDEX
    Explanations

    references to people and their relationships

    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
    0:0.04
    1:0.03
    2:0.04
    3:0.15
    4:0.01
    5:0.14
    6:0.02
    7:0.07
    8:0.02
    9:0.01
    10:0.40
    11:0.02
    Negative Logits
     circumstances
    -1.99
    egu
    -1.99
    メ
    -1.94
    monary
    -1.91
    ilial
    -1.87
    ourt
    -1.86
    eria
    -1.83
    mia
    -1.81
    served
    -1.79
    pite
    -1.77
    POSITIVE LOGITS
     dominance
    1.80
    Activity
    1.77
    flat
    1.76
    uer
    1.73
    recated
    1.71
    itan
    1.68
     repeatedly
    1.63
    WER
    1.60
    uers
    1.60
    �
    1.60
    Activations Density 0.150%

    No Known Activations