© 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. 3337
    Prev
    Next
    INDEX
    Explanations

    references to ratings or scores, particularly in numeric form

    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
    0:0.07
    1:0.21
    2:0.04
    3:0.08
    4:0.06
    5:0.13
    6:0.04
    7:0.04
    8:0.12
    9:0.07
    10:0.03
    11:0.06
    Negative Logits
     null
    -2.58
    SHIP
    -2.25
    renheit
    -2.24
     corrid
    -2.17
     Gamergate
    -2.15
     mund
    -2.14
     FAT
    -2.14
     milliseconds
    -2.10
    ��極
    -2.09
    quickShipAvailable
    -2.08
    POSITIVE LOGITS
    4
    2.94
    5
    2.89
    6
    2.64
     externalToEVAOnly
    2.56
    also
    2.47
    3
    2.44
    7
    2.29
    semble
    2.21
    8
    2.18
    Likewise
    2.17
    Activations Density 0.001%

    No Known Activations