© 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. 21427
    Prev
    Next
    INDEX
    Explanations

    web links and references

    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
    0:0.12
    1:0.03
    2:0.03
    3:0.06
    4:0.02
    5:0.04
    6:0.19
    7:0.04
    8:0.07
    9:0.27
    10:0.02
    11:0.05
    Negative Logits
     BB
    -3.55
     Brighton
    -3.48
    igham
    -3.40
    icone
    -3.09
    Wing
    -3.07
    ettel
    -3.04
     plush
    -3.01
    Virgin
    -3.01
    Wan
    -3.00
     Velvet
    -2.99
    POSITIVE LOGITS
    NPR
    8.57
     NPR
    8.05
    toggle
    4.20
    RN
    4.17
     CBC
    4.00
    Radio
    3.74
     Jonas
    3.70
     RN
    3.66
     Lori
    3.58
    radio
    3.52
    Activations Density 0.000%

    No Known Activations