© 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. 21350
    Prev
    Next
    INDEX
    Explanations

    items and concepts related to gaming and narrative experiences

    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
    2:0.03
    3:0.04
    4:0.06
    5:0.39
    6:0.02
    7:0.03
    8:0.02
    9:0.20
    10:0.02
    11:0.08
    Negative Logits
     ALSO
    -3.83
    Moreover
    -3.61
     furthermore
    -3.22
    etheless
    -3.20
    Furthermore
    -3.19
     moreover
    -3.15
     also
    -2.88
     likewise
    -2.85
    Legal
    -2.83
    sylv
    -2.80
    POSITIVE LOGITS
    .):
    3.18
     versus
    3.18
     tossed
    3.06
     shoved
    2.87
     minus
    2.85
     instead
    2.78
     except
    2.65
     slapped
    2.64
     stuffed
    2.59
     stripped
    2.58
    Activations Density 0.245%

    No Known Activations