© 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. 22995
    Prev
    Next
    INDEX
    Explanations

    instances of text messaging and related legal responsibilities

    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
    0:0.18
    1:0.04
    2:0.06
    3:0.05
    4:0.04
    5:0.05
    6:0.14
    7:0.03
    8:0.03
    9:0.27
    10:0.03
    11:0.03
    Negative Logits
     Cay
    -4.21
     Beir
    -4.20
    Kin
    -3.98
     McKin
    -3.93
     Kear
    -3.71
     Manit
    -3.45
     Pike
    -3.43
    cair
    -3.38
     Eag
    -3.38
    ierre
    -3.35
    POSITIVE LOGITS
     Text
    8.42
     text
    8.18
    Text
    8.00
    text
    8.00
     TEXT
    7.58
     texts
    7.17
    TEXT
    6.81
     texting
    6.67
     textual
    5.98
     texted
    5.31
    Activations Density 0.018%

    No Known Activations