© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 14044
    Prev
    Next
    INDEX
    Explanations

    references to research studies or reports related to social issues

    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
    2:0.10
    3:0.24
    4:0.11
    5:0.06
    6:0.02
    7:0.07
    8:0.08
    9:0.02
    10:0.14
    11:0.05
    Negative Logits
    ‑
    -2.44
    iking
    -2.19
    leep
    -2.17
    luster
    -2.14
    astic
    -2.09
     lov
    -2.07
    roph
    -2.06
    ¯
    -2.05
    adin
    -2.03
    canon
    -2.03
    POSITIVE LOGITS
     Reuters
    3.02
     campaigners
    2.87
     ARTICLE
    2.77
     Amnesty
    2.66
     organisers
    2.66
    Reuters
    2.60
     analysts
    2.60
     proposals
    2.60
     NYT
    2.57
    ccording
    2.55
    Activations Density 0.583%

    No Known Activations