© 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. 213
    Prev
    Next
    INDEX
    Explanations

    references to specifications and features of hardware, particularly relating to video processing

    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
    0:0.12
    1:0.04
    2:0.06
    3:0.03
    4:0.06
    5:0.03
    6:0.22
    7:0.07
    8:0.11
    9:0.16
    10:0.02
    11:0.04
    Negative Logits
     teasp
    -4.61
     fri
    -4.00
    olesterol
    -3.99
    Champ
    -3.90
     mmol
    -3.85
    kef
    -3.84
     sugar
    -3.84
    idad
    -3.67
    gage
    -3.63
     syrup
    -3.42
    POSITIVE LOGITS
     Orion
    11.59
     Allen
    4.60
     Lev
    4.56
     Perse
    4.53
     Nim
    4.53
     Merlin
    4.48
     Saturn
    4.47
     Pegasus
    4.43
     Miranda
    4.41
     Horus
    4.40
    Activations Density 0.001%

    No Known Activations