© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 21180
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their actions or characteristics within a narrative 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
    0:0.09
    1:0.15
    2:0.07
    3:0.03
    4:0.03
    5:0.02
    6:0.05
    7:0.08
    8:0.02
    9:0.04
    10:0.34
    11:0.04
    Negative Logits
    ciating
    -3.14
    ��
    -3.13
    ember
    -2.97
     Pap
    -2.93
    ivery
    -2.90
     CAP
    -2.79
    cit
    -2.74
    carbon
    -2.73
     Sawyer
    -2.71
    edge
    -2.68
    POSITIVE LOGITS
     Lo
    10.17
    Lo
    8.68
     lo
    6.75
    lo
    6.52
     LO
    6.12
    LO
    5.08
     Ho
    4.65
    Mo
    4.51
    Ho
    4.40
     MO
    4.26
    Activations Density 0.011%

    No Known Activations