© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 14153
    Prev
    Next
    INDEX
    Explanations

    references to articles, authors, and reports related to public statements or events

    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
    0:0.05
    1:0.01
    2:0.06
    3:0.49
    4:0.05
    5:0.07
    6:0.04
    7:0.03
    8:0.03
    9:0.04
    10:0.07
    11:0.02
    Negative Logits
     hospitals
    -2.58
     legislatures
    -2.38
     supermarkets
    -2.36
     theaters
    -2.34
     shelters
    -2.30
     councils
    -2.22
     airports
    -2.22
     plantations
    -2.19
     churches
    -2.18
     clinics
    -2.17
    POSITIVE LOGITS
    haired
    2.76
     frontman
    2.60
     captain
    2.26
     Chaser
    2.21
    jad
    2.21
     youngster
    2.20
    hander
    2.15
    uncle
    2.09
    agonist
    2.08
     footballer
    2.06
    Activations Density 1.671%

    No Known Activations