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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 7774
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific repeated characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.10
    2:0.11
    3:0.04
    4:0.04
    5:0.08
    6:0.10
    7:0.09
    8:0.10
    9:0.05
    10:0.09
    11:0.11
    Negative Logits
     tyres
    -1.14
    itaire
    -1.04
     privile
    -1.03
     degrading
    -1.00
     outweigh
    -0.99
     requiring
    -0.95
    pson
    -0.92
     Grind
    -0.92
     skewed
    -0.91
     aura
    -0.91
    POSITIVE LOGITS
     HOU
    1.09
    USS
    1.08
     STUD
    1.07
    CLASSIFIED
    1.05
    版
    1.05
     OFFIC
    1.01
     Evening
    1.00
    atted
    0.99
     SOLD
    0.99
    aturdays
    0.99
    Activations Density 0.214%

    No Known Activations