© 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. 5-ATT-KK
    11. 28948
    Prev
    Next
    INDEX
    Explanations

    the word "so."

    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
    0:0.07
    1:0.11
    2:0.10
    3:0.08
    4:0.07
    5:0.07
    6:0.06
    7:0.07
    8:0.09
    9:0.07
    10:0.08
    11:0.08
    Negative Logits
    Hide
    -1.74
    Attach
    -1.71
    doi
    -1.59
    rw
    -1.56
    igs
    -1.54
    grave
    -1.54
    abilities
    -1.53
    Rat
    -1.52
    idav
    -1.51
    RW
    -1.49
    POSITIVE LOGITS
    ë
    1.59
    onna
    1.55
    aceous
    1.48
     expelled
    1.42
     raped
    1.40
    enium
    1.37
     ®
    1.37
     proud
    1.36
    opausal
    1.35
    è
    1.35
    Activations Density 0.000%

    No Known Activations