© 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. 3328
    Prev
    Next
    INDEX
    Explanations

    references to archaeological evidence or discoveries

    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
    1:0.02
    2:0.14
    3:0.16
    4:0.03
    5:0.25
    6:0.03
    7:0.04
    8:0.06
    9:0.02
    10:0.06
    11:0.02
    Negative Logits
    heit
    -1.74
     IPM
    -1.72
     blogging
    -1.70
    natureconservancy
    -1.67
    ictions
    -1.65
    blog
    -1.63
    %:
    -1.63
     intens
    -1.62
     blogs
    -1.62
     admins
    -1.59
    POSITIVE LOGITS
    liest
    2.06
    lled
    1.76
     sacked
    1.75
     Samson
    1.72
     vanished
    1.72
    bone
    1.71
     prehistoric
    1.70
     buried
    1.64
     burial
    1.61
    ⓘ
    1.61
    Activations Density 0.409%

    No Known Activations