© 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. 473
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols

    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
    0:0.06
    1:0.16
    2:0.05
    3:0.08
    4:0.07
    5:0.14
    6:0.05
    7:0.13
    8:0.06
    9:0.05
    10:0.05
    11:0.06
    Negative Logits
     messenger
    -2.61
     Lynn
    -2.60
    �
    -2.47
    Sean
    -2.36
     Mrs
    -2.33
     Natalie
    -2.32
     Nurse
    -2.27
     silenced
    -2.27
     polar
    -2.23
     Ms
    -2.20
    POSITIVE LOGITS
    icc
    2.88
    ACA
    2.73
    avascript
    2.71
    artz
    2.69
    isode
    2.64
    acc
    2.63
    eca
    2.57
    ternity
    2.56
    acteria
    2.54
    odic
    2.54
    Activations Density 0.000%

    No Known Activations