© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 10873
    Prev
    Next
    INDEX
    Explanations

    discourse about unlimited data plans and their implications

    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
    1:0.04
    2:0.23
    3:0.07
    4:0.05
    5:0.11
    6:0.05
    7:0.05
    8:0.04
    9:0.07
    10:0.04
    11:0.04
    Negative Logits
     Normandy
    -2.72
    rique
    -2.65
     sighting
    -2.53
     Forensic
    -2.47
     Constable
    -2.39
     Salv
    -2.39
     Rifle
    -2.38
     Hussain
    -2.36
    RN
    -2.35
     FN
    -2.31
    POSITIVE LOGITS
     thrott
    4.95
     caps
    3.93
     capped
    3.68
     throttle
    3.64
    Limit
    3.29
     bandwidth
    3.28
     cap
    3.28
     unlimited
    3.25
     limit
    3.24
     streaming
    3.20
    Activations Density 0.005%

    No Known Activations