© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 19052
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific individual in a context that suggests urgent or serious matters

    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
    0:0.05
    1:0.20
    2:0.06
    3:0.06
    4:0.06
    5:0.05
    6:0.10
    7:0.06
    8:0.04
    9:0.16
    10:0.06
    11:0.05
    Negative Logits
    JECT
    -2.99
    fff
    -2.94
    ITCH
    -2.89
     masks
    -2.88
     dup
    -2.87
    Dream
    -2.87
     dom
    -2.85
    Reloaded
    -2.81
     Cunningham
    -2.76
    Alert
    -2.66
    POSITIVE LOGITS
    Interstitial
    3.46
     Xin
    3.11
     Argon
    2.94
    ukong
    2.85
    uthor
    2.82
    pered
    2.75
    Reviewer
    2.71
    ococ
    2.71
    isoft
    2.68
    stellar
    2.68
    Activations Density 0.001%

    No Known Activations