© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 3689
    Prev
    Next
    INDEX
    Explanations

    key points related to political events and figures

    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
    1:0.03
    2:0.06
    3:0.10
    4:0.04
    5:0.06
    6:0.02
    7:0.44
    8:0.05
    9:0.01
    10:0.06
    11:0.02
    Negative Logits
    cellent
    -2.80
    morrow
    -2.48
     �
    -2.30
    �
    -2.26
    龍契士
    -2.25
    pai
    -2.22
    arest
    -2.21
     kisses
    -2.19
    yip
    -2.19
     beware
    -2.15
    POSITIVE LOGITS
    then
    3.83
     then
    3.75
    later
    3.74
     subsequently
    3.20
     subsequent
    3.17
     Then
    3.04
     thereafter
    2.88
    was
    2.73
     THEN
    2.71
     later
    2.69
    Activations Density 1.235%

    No Known Activations