© 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. 21394
    Prev
    Next
    INDEX
    Explanations

    phrases indicating position or status within a context

    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
    0:0.08
    1:0.07
    2:0.06
    3:0.08
    4:0.07
    5:0.09
    6:0.09
    7:0.09
    8:0.07
    9:0.08
    10:0.08
    11:0.09
    Negative Logits
     Madden
    -2.67
     Summoner
    -2.61
    onday
    -2.60
     Franchise
    -2.60
     Exile
    -2.55
     Hayward
    -2.48
    Delete
    -2.47
    DH
    -2.46
    tymology
    -2.46
    etts
    -2.44
    POSITIVE LOGITS
    cule
    2.43
    vas
    2.43
    eros
    2.31
     Rus
    2.24
     expans
    2.23
    urs
    2.21
    Sov
    2.21
    IRE
    2.18
    izont
    2.18
    imir
    2.17
    Activations Density 0.000%

    No Known Activations