© 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. 9759
    Prev
    Next
    INDEX
    Explanations

    pricing details and comparisons related to food shopping

    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
    0:0.04
    1:0.03
    2:0.06
    3:0.30
    4:0.07
    5:0.09
    6:0.05
    7:0.08
    8:0.04
    9:0.06
    10:0.09
    11:0.04
    Negative Logits
     reper
    -2.47
     recount
    -2.38
     satir
    -2.29
     epigen
    -2.27
     reconnect
    -2.27
     archaeologists
    -2.19
     puzz
    -2.16
     scrut
    -2.15
     geological
    -2.13
     redund
    -2.11
    POSITIVE LOGITS
    %:
    2.63
     Offense
    2.47
    Hig
    2.46
     Starting
    2.41
    *:
    2.40
     Basics
    2.39
    ":{"
    2.32
     Starts
    2.31
    ♦
    2.29
     Avg
    2.23
    Activations Density 0.599%

    No Known Activations