© 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. 19022
    Prev
    Next
    INDEX
    Explanations

    references to secure or classified information and the context of its distribution

    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
    0:0.10
    1:0.03
    2:0.08
    3:0.05
    4:0.08
    5:0.05
    6:0.19
    7:0.04
    8:0.14
    9:0.12
    10:0.03
    11:0.04
    Negative Logits
    ijah
    -3.94
    ylon
    -3.91
    verbs
    -3.48
    kn
    -3.48
    bey
    -3.45
     Clifford
    -3.29
     carrot
    -3.27
    Els
    -3.23
    arrow
    -3.23
    byn
    -3.20
    POSITIVE LOGITS
     SAP
    10.10
     Sapphire
    5.66
     Sap
    5.01
     Saras
    4.47
     Caf
    4.39
     Radeon
    4.36
     Cit
    4.32
     Dana
    4.28
     SAS
    4.16
    Sand
    4.15
    Activations Density 0.000%

    No Known Activations