© 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. 9-ATT-KK
    11. 8960
    Prev
    Next
    INDEX
    Explanations

    phrases related to languages and their usage

    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
    1:0.14
    2:0.03
    3:0.14
    4:0.07
    5:0.17
    6:0.03
    7:0.13
    8:0.05
    9:0.02
    10:0.04
    11:0.05
    Negative Logits
     literacy
    -2.94
     illiter
    -2.88
     immigrants
    -2.74
     textbooks
    -2.72
     exams
    -2.71
     horr
    -2.71
     linguistic
    -2.67
     sectarian
    -2.67
     clerics
    -2.66
    Muslims
    -2.65
    POSITIVE LOGITS
    attery
    2.97
     Matthews
    2.74
     Decker
    2.66
     Bunker
    2.59
     Rutherford
    2.58
     Bounce
    2.47
     Muller
    2.38
     Peb
    2.36
     Pump
    2.35
    mallow
    2.35
    Activations Density 0.002%

    No Known Activations