© 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. 1512
    Prev
    Next
    INDEX
    Explanations

    components related to product announcements and availability

    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
    0:0.15
    1:0.03
    2:0.13
    3:0.15
    4:0.05
    5:0.14
    6:0.05
    7:0.08
    8:0.06
    9:0.04
    10:0.06
    11:0.02
    Negative Logits
     ARTICLE
    -2.35
     Ruin
    -2.07
    enance
    -2.00
    xon
    -1.95
    obin
    -1.93
    bage
    -1.88
     foul
    -1.86
    wikipedia
    -1.84
    ascript
    -1.80
    Wik
    -1.80
    POSITIVE LOGITS
     deliveries
    3.08
     rollout
    2.77
     prototypes
    2.72
     testers
    2.47
     debut
    2.42
    Delivery
    2.32
    sold
    2.25
     shipments
    2.18
     trials
    2.18
     customers
    2.17
    Activations Density 0.195%

    No Known Activations