© 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. 12242
    Prev
    Next
    INDEX
    Explanations

    tokens and references to groups or entities

    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
    0:0.08
    1:0.05
    2:0.05
    3:0.10
    4:0.09
    5:0.07
    6:0.14
    7:0.05
    8:0.06
    9:0.15
    10:0.05
    11:0.05
    Negative Logits
     Anthem
    -2.85
     Em
    -2.65
     Ely
    -2.63
     Miranda
    -2.60
     Highlights
    -2.53
    Em
    -2.47
     Quin
    -2.47
    rium
    -2.44
     Elect
    -2.43
    itialized
    -2.43
    POSITIVE LOGITS
     swim
    3.10
     fisher
    3.07
     cous
    2.95
     crocod
    2.91
     ski
    2.90
     fisheries
    2.85
     knitting
    2.81
     teasp
    2.75
     poaching
    2.73
     submar
    2.72
    Activations Density 0.000%

    No Known Activations