© 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. 22263
    Prev
    Next
    INDEX
    Explanations

    references to scores or statistics related to sports events

    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
    0:0.05
    1:0.02
    2:0.06
    3:0.14
    4:0.09
    5:0.07
    6:0.04
    7:0.17
    8:0.10
    9:0.13
    10:0.02
    11:0.04
    Negative Logits
     ();
    -2.70
    \":
    -2.62
    ];
    -2.53
     whilst
    -2.44
    %;
    -2.36
     ];
    -2.26
    ';
    -2.25
     ());
    -2.24
    ‐
    -2.21
     ;
    -2.11
    POSITIVE LOGITS
    tsy
    2.52
     Etsy
    2.51
    etsy
    2.29
    Email
    2.21
    hig
    2.21
    abbit
    2.20
     Schne
    2.15
     Suz
    2.12
    My
    2.10
    hello
    2.09
    Activations Density 0.000%

    No Known Activations