Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 44435
    Prev
    Next
    INDEX
    Explanations

    expressions of personal assertion or confidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    1:0.01
    2:0.11
    3:0.11
    4:0.12
    5:0.04
    6:0.25
    7:0.04
    8:0.06
    9:0.04
    10:0.05
    11:0.09
    Negative Logits
    BILITIES
    -1.38
    Discover
    -1.35
    Publisher
    -1.31
    Offline
    -1.28
    Exit
    -1.26
    eeds
    -1.26
    RET
    -1.26
    Rated
    -1.24
    Ability
    -1.23
    laim
    -1.16
    POSITIVE LOGITS
     wonders
    1.34
    ilo
    1.30
     helicop
    1.26
     unpop
    1.25
     Pau
    1.25
     Carson
    1.22
    soDeliveryDate
    1.21
    behind
    1.18
     Sung
    1.17
     Watts
    1.17
    Activations Density 0.001%

    No Known Activations