© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 9678
    Prev
    Next
    INDEX
    Explanations

    sentences that convey sequenced actions or events

    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
    0:0.09
    1:0.01
    2:0.05
    3:0.03
    4:0.04
    5:0.03
    6:0.27
    7:0.04
    8:0.07
    9:0.27
    10:0.02
    11:0.02
    Negative Logits
     Obj
    -4.13
     Dinosaur
    -3.90
    olkien
    -3.90
     illeg
    -3.89
     gobl
    -3.86
     Sloven
    -3.85
     lava
    -3.65
     Mn
    -3.62
     Minion
    -3.44
     Coffin
    -3.40
    POSITIVE LOGITS
     Shaw
    11.91
    shaw
    6.77
     Chow
    5.16
     SQU
    4.92
     Sawyer
    4.75
     Shu
    4.64
     Shapiro
    4.59
     Shar
    4.36
    Sh
    4.32
     Sham
    4.24
    Activations Density 0.002%

    No Known Activations