© 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 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. 9371
    Prev
    Next
    INDEX
    Explanations

    software installation instructions related to specific programs and drivers

    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
    0:0.07
    1:0.03
    2:0.02
    3:0.17
    4:0.08
    5:0.14
    6:0.06
    7:0.03
    8:0.04
    9:0.06
    10:0.10
    11:0.12
    Negative Logits
     basil
    -2.40
     Mara
    -2.38
     Kad
    -2.35
     Haram
    -2.28
     bracelet
    -2.21
    Amazon
    -2.10
     obligatory
    -2.09
     deity
    -2.03
     glyphosate
    -2.02
     occult
    -2.01
    POSITIVE LOGITS
    \
    4.09
    \)
    3.52
    \<
    3.34
    \.
    3.29
    sbm
    3.15
    Û
    3.00
    \",
    2.96
    /​
    2.96
    hov
    2.80
    }\
    2.79
    Activations Density 0.007%

    No Known Activations