© 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. 19116
    Prev
    Next
    INDEX
    Explanations

    references to specific actions or events related to construction or creation

    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
    0:0.22
    1:0.03
    2:0.07
    3:0.05
    4:0.06
    5:0.03
    6:0.15
    7:0.05
    8:0.08
    9:0.14
    10:0.02
    11:0.04
    Negative Logits
    Fa
    -3.15
     裏�
    -3.04
     subst
    -3.02
    ggies
    -3.02
    FACE
    -2.98
     usur
    -2.98
    atchewan
    -2.96
    ═
    -2.93
    975
    -2.92
     swamp
    -2.91
    POSITIVE LOGITS
     Kod
    10.20
     Ern
    5.18
     Shot
    4.22
     Nikon
    4.18
     Koz
    4.13
     Kov
    3.92
    Magazine
    3.84
     Film
    3.75
     Leica
    3.68
     Kard
    3.63
    Activations Density 0.000%

    No Known Activations