© 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. 9-ATT-KK
    11. 15873
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals, companies, and organizations

    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
    2:0.04
    3:0.16
    4:0.02
    5:0.04
    6:0.02
    7:0.04
    8:0.02
    9:0.02
    10:0.49
    11:0.02
    Negative Logits
    whether
    -2.26
    aned
    -2.21
    how
    -2.19
     interacts
    -2.15
    worst
    -2.14
    stood
    -2.14
    usually
    -2.11
    acceptable
    -2.10
    readable
    -2.04
    accessible
    -2.03
    POSITIVE LOGITS
     bandwagon
    2.32
     Else
    2.21
     together
    2.14
     anew
    1.96
     alongside
    1.96
     herd
    1.91
     forces
    1.89
    WD
    1.86
     regulars
    1.86
     shortly
    1.86
    Activations Density 0.076%

    No Known Activations