© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 5443
    Prev
    Next
    INDEX
    Explanations

    names and words associated with people or groups in various contexts

    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
    0:0.04
    1:0.01
    2:0.05
    3:0.07
    4:0.02
    5:0.04
    6:0.01
    7:0.03
    8:0.02
    9:0.01
    10:0.64
    11:0.02
    Negative Logits
    ゼウス
    -2.23
    isSpecialOrderable
    -2.19
    Introduced
    -2.02
    Untitled
    -2.00
     Unsure
    -1.97
    BuyableInstoreAndOnline
    -1.92
    opian
    -1.92
    ト
    -1.84
     recess
    -1.83
     vantage
    -1.82
    POSITIVE LOGITS
     for
    4.21
    for
    3.71
     FOR
    2.85
     For
    2.54
    For
    2.46
    FOR
    2.15
     because
    2.13
     harshly
    2.03
    龍
    1.90
    arag
    1.82
    Activations Density 0.973%

    No Known Activations