© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 4188
    Prev
    Next
    INDEX
    Explanations

    conversational phrases that express uncertainty or advice

    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
    0:0.03
    1:0.02
    2:0.05
    3:0.16
    4:0.06
    5:0.07
    6:0.15
    7:0.04
    8:0.06
    9:0.09
    10:0.10
    11:0.11
    Negative Logits
    ────────
    -1.38
     裏覚醒
    -1.31
    %:
    -1.29
     Rak
    -1.28
    untled
    -1.27
    official
    -1.26
    ═
    -1.21
    Released
    -1.20
    Beg
    -1.19
    rament
    -1.18
    POSITIVE LOGITS
     Topic
    1.42
     Nato
    1.35
     proverb
    1.32
     ['
    1.28
    )."
    1.28
    ictionary
    1.27
     gotta
    1.23
    IER
    1.22
     diction
    1.18
     imagine
    1.18
    Activations Density 0.101%

    No Known Activations