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. 44446
    Prev
    Next
    INDEX
    Explanations

    temporal references related to time periods, focusing on "this" and "last" to indicate current or previous events

    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
    0:0.02
    1:0.02
    2:0.06
    3:0.04
    4:0.13
    5:0.03
    6:0.24
    7:0.17
    8:0.04
    9:0.04
    10:0.07
    11:0.08
    Negative Logits
    ァ
    -1.35
    ォ
    -1.35
    イト
    -1.26
    BLIC
    -1.24
     surrogate
    -1.23
    iasco
    -1.23
    BIL
    -1.22
     cooperative
    -1.16
    �
    -1.15
     distract
    -1.13
    POSITIVE LOGITS
     Britann
    1.19
     Sussex
    1.13
     Notting
    1.12
     Powder
    1.11
     Sebast
    1.10
     Yon
    1.10
    reply
    1.09
     Abyss
    1.07
    estate
    1.07
    Reply
    1.06
    Activations Density 0.001%

    No Known Activations