© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-ATT-KK
    11. 3605
    Prev
    Next
    INDEX
    Explanations

    connections between memory, wisdom, and community awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    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
    2:0.07
    3:0.17
    4:0.07
    5:0.07
    6:0.04
    7:0.25
    8:0.06
    9:0.04
    10:0.04
    11:0.07
    Negative Logits
    ftime
    -2.48
    perty
    -2.27
    �
    -2.06
    iator
    -2.04
    celer
    -2.01
    ソ
    -1.91
    wayne
    -1.90
     Instant
    -1.88
    ゴン
    -1.87
    IU
    -1.85
    POSITIVE LOGITS
    their
    6.56
    Their
    5.88
     THEIR
    5.85
    they
    5.68
    They
    5.45
     their
    5.16
     THEY
    5.10
     Their
    5.08
     theirs
    5.08
     themselves
    4.93
    Activations Density 1.165%

    No Known Activations