© 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. 459
    Prev
    Next
    INDEX
    Explanations

    partnerships and collaborative efforts related to business expansion

    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
    1:0.01
    2:0.11
    3:0.27
    4:0.04
    5:0.15
    6:0.02
    7:0.11
    8:0.04
    9:0.01
    10:0.09
    11:0.01
    Negative Logits
     grop
    -2.40
     asshole
    -2.23
     whining
    -2.22
     blame
    -2.20
     vomit
    -2.19
     gore
    -2.19
     doct
    -2.18
     poop
    -2.16
     blaming
    -2.13
     bullshit
    -2.11
    POSITIVE LOGITS
     innovative
    3.11
     excellence
    2.77
     unparalleled
    2.73
     exciting
    2.70
     unmatched
    2.67
     innovation
    2.65
     groundbreaking
    2.65
     innovations
    2.59
     partnership
    2.58
     vibrant
    2.56
    Activations Density 1.309%

    No Known Activations