© 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. 5-ATT-KK
    11. 3262
    Prev
    Next
    INDEX
    Explanations

    social media references and hashtags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.03
    2:0.04
    3:0.11
    4:0.07
    5:0.05
    6:0.04
    7:0.05
    8:0.06
    9:0.05
    10:0.08
    11:0.33
    Negative Logits
    flag
    -1.74
    andise
    -1.73
     jam
    -1.63
     anthem
    -1.60
     flag
    -1.57
    76561
    -1.54
     Flag
    -1.52
    endars
    -1.51
    �
    -1.50
    AAF
    -1.50
    POSITIVE LOGITS
     unemploy
    1.75
     confinement
    1.68
    inav
    1.59
     malnutrition
    1.56
    levels
    1.51
     Gord
    1.50
    eger
    1.49
     Processing
    1.47
     Classification
    1.45
     Gupta
    1.44
    Activations Density 0.038%

    No Known Activations