© 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. 12256
    Prev
    Next
    INDEX
    Explanations

    information related to the indie gaming industry and its challenges

    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
    0:0.12
    1:0.11
    2:0.06
    3:0.06
    4:0.07
    5:0.03
    6:0.09
    7:0.17
    8:0.02
    9:0.06
    10:0.08
    11:0.09
    Negative Logits
    osterone
    -2.60
    %%%%
    -2.50
    ��
    -2.48
    Repe
    -2.47
    �
    -2.47
    Downloadha
    -2.45
    Football
    -2.44
    obyl
    -2.43
     erection
    -2.34
    Temperature
    -2.32
    POSITIVE LOGITS
     indie
    4.91
     Indie
    4.63
     ind
    3.20
     devs
    2.94
     publishers
    2.76
     creat
    2.70
     Sony
    2.63
     independents
    2.60
     Vert
    2.59
     PS
    2.55
    Activations Density 0.005%

    No Known Activations