© 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. 2700
    Prev
    Next
    INDEX
    Explanations

    mentions of user handles or usernames, particularly in a social media context

    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
    0:0.11
    1:0.05
    2:0.05
    3:0.08
    4:0.07
    5:0.05
    6:0.18
    7:0.07
    8:0.06
    9:0.15
    10:0.03
    11:0.04
    Negative Logits
     Aud
    -3.37
     Fred
    -3.27
     Brian
    -3.25
     Benn
    -3.22
    Brend
    -3.20
     Bob
    -3.15
     Betty
    -3.05
    Band
    -3.02
     Bron
    -2.97
     Brendan
    -2.97
    POSITIVE LOGITS
     ramps
    3.18
     latt
    3.01
     Riyadh
    2.94
     tofu
    2.94
     hydra
    2.91
    Tile
    2.79
     Tillerson
    2.78
     Tripoli
    2.77
     depreciation
    2.75
     SEA
    2.72
    Activations Density 0.000%

    No Known Activations