© 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. 9972
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or event identifiers

    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
    1:0.01
    2:0.01
    3:0.17
    4:0.06
    5:0.13
    6:0.02
    7:0.32
    8:0.01
    9:0.01
    10:0.10
    11:0.02
    Negative Logits
    quartered
    -2.63
     destro
    -2.35
    ichever
    -2.33
     conflic
    -2.18
     influences
    -2.11
     exert
    -2.08
     cartridge
    -2.06
    wcsstore
    -2.06
     acquaint
    -2.04
     presentations
    -2.04
    POSITIVE LOGITS
    pic
    3.28
     pic
    3.05
    OTUS
    2.49
     Ivanka
    2.48
    DN
    2.45
    Quote
    2.45
    Gaza
    2.44
    FY
    2.41
    ylum
    2.40
    ickr
    2.38
    Activations Density 0.006%

    No Known Activations