© 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. 3791
    Prev
    Next
    INDEX
    Explanations

    names of people, organizations, and events related to entertainment and sports

    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
    2:0.06
    3:0.19
    4:0.31
    5:0.04
    6:0.04
    7:0.03
    8:0.04
    9:0.06
    10:0.07
    11:0.05
    Negative Logits
     advantageous
    -2.13
    notation
    -1.94
    cessive
    -1.92
    etheless
    -1.91
    iqueness
    -1.90
    alties
    -1.90
     undesirable
    -1.89
    notations
    -1.88
     disadvantage
    -1.84
     detrimental
    -1.83
    POSITIVE LOGITS
     (@
    2.89
     Rae
    1.92
    版
    1.91
    =#
    1.67
     Films
    1.59
     Sent
    1.58
     Flo
    1.57
     Pix
    1.56
     Gang
    1.56
     Panda
    1.53
    Activations Density 0.039%

    No Known Activations