© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 19163
    Prev
    Next
    INDEX
    Explanations

    references to technological development and potential risks associated with emerging technologies

    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
    0:0.31
    1:0.01
    2:0.18
    3:0.10
    4:0.02
    5:0.07
    6:0.03
    7:0.04
    8:0.04
    9:0.02
    10:0.11
    11:0.01
    Negative Logits
     booking
    -2.35
     handwritten
    -2.28
     quotas
    -2.21
     Fill
    -2.21
     stuffing
    -2.19
     gallon
    -2.17
     abdom
    -2.13
     staffing
    -2.12
     fret
    -2.09
    Gi
    -2.09
    POSITIVE LOGITS
    Technology
    3.24
     prototype
    3.13
     technologies
    3.01
    technology
    2.98
     technology
    2.86
     pioneer
    2.85
     Technology
    2.81
     Technologies
    2.81
     inventor
    2.79
     prototypes
    2.77
    Activations Density 0.041%

    No Known Activations