© 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. 10-ATT-KK
    11. 12756
    Prev
    Next
    INDEX
    Explanations

    words associated with knowledge and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.03
    2:0.09
    3:0.34
    4:0.15
    5:0.12
    6:0.02
    7:0.03
    8:0.03
    9:0.04
    10:0.02
    11:0.03
    Negative Logits
     recognise
    -7.20
     realise
    -6.83
     realised
    -6.67
     (£
    -6.19
     recognised
    -6.08
     organise
    -6.07
     programme
    -6.02
     organisation
    -5.93
     arte
    -5.85
     organis
    -5.85
    POSITIVE LOGITS
    .,"
    5.70
    ;"
    5.57
    "—
    5.33
    ,''
    4.79
    ,"
    4.76
    ,"
    4.73
    —"
    4.70
    .")
    4.59
    ,'"
    4.59
    ),"
    4.58
    Activations Density 0.037%

    No Known Activations