© 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. 20192
    Prev
    Next
    INDEX
    Explanations

    references to individuals or entities making claims or statements

    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
    1:0.02
    2:0.08
    3:0.17
    4:0.02
    5:0.11
    6:0.02
    7:0.03
    8:0.03
    9:0.03
    10:0.37
    11:0.02
    Negative Logits
     saying
    -2.08
     explaining
    -2.00
     plaint
    -1.99
     Suggest
    -1.97
     introdu
    -1.95
    ikarp
    -1.90
     Revelations
    -1.87
    escription
    -1.87
     announcing
    -1.85
     Guess
    -1.81
    POSITIVE LOGITS
     indeed
    3.13
     lacks
    2.70
     actively
    2.61
     possesses
    2.60
     exists
    2.56
     actually
    2.50
     exceeded
    2.44
     significantly
    2.41
     thri
    2.40
     exceeds
    2.40
    Activations Density 0.545%

    No Known Activations