© 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. 27274
    Prev
    Next
    INDEX
    Explanations

    sections of text marked by slashes

    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
    0:0.14
    1:0.14
    2:0.06
    3:0.07
    4:0.05
    5:0.08
    6:0.06
    7:0.04
    8:0.12
    9:0.07
    10:0.06
    11:0.04
    Negative Logits
     Sally
    -1.74
     Sno
    -1.70
     Chong
    -1.70
     Oprah
    -1.65
     Bigfoot
    -1.65
     Playboy
    -1.65
     Pepsi
    -1.60
     Frankie
    -1.60
     Ray
    -1.56
     fr
    -1.53
    POSITIVE LOGITS
    esm
    2.38
    arten
    2.19
    thora
    2.19
    ommel
    2.11
    lement
    2.02
    erker
    2.01
    erd
    2.00
    alion
    1.96
    �
    1.94
    adian
    1.93
    Activations Density 0.000%

    No Known Activations