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. 9-ATT-KK
    6. 7650
    Prev
    Next
    INDEX
    Explanations

    brackets and punctuation marks, indicating structure or references within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.29
    2:0.03
    3:0.07
    4:0.10
    5:0.11
    6:0.11
    7:0.05
    8:0.03
    9:0.03
    10:0.03
    11:0.06
    Negative Logits
     XT
    -2.31
    ================================================================
    -2.30
     infall
    -2.23
     increasingly
    -2.18
    CHAT
    -2.12
    roph
    -2.12
    EStream
    -2.09
    ◼
    -2.03
     FORM
    -2.03
     CODE
    -2.02
    POSITIVE LOGITS
    notes
    2.85
    cia
    2.52
    cor
    2.45
    note
    2.38
    individual
    2.38
    nor
    2.35
    inelli
    2.33
    3
    2.32
    unci
    2.24
     heterogeneity
    2.20
    Activations Density 0.018%

    No Known Activations