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. 7764
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a high frequency or intensity of an experience or evaluation

    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
    0:0.02
    1:0.02
    2:0.08
    3:0.30
    4:0.01
    5:0.02
    6:0.12
    7:0.04
    8:0.06
    9:0.05
    10:0.11
    11:0.12
    Negative Logits
    ーテ
    -1.50
    orer
    -1.36
    inav
    -1.30
    aring
    -1.28
     Chamberlain
    -1.28
    ouri
    -1.25
    uer
    -1.23
    alian
    -1.23
    enment
    -1.22
    ONSORED
    -1.20
    POSITIVE LOGITS
    illet
    1.32
     resume
    1.32
     resumes
    1.30
    bart
    1.25
    Trade
    1.20
     funer
    1.15
    atom
    1.09
    punk
    1.07
    uple
    1.03
    ---------------
    1.03
    Activations Density 0.008%

    No Known Activations