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. 7858
    Prev
    Next
    INDEX
    Explanations

    specific names and titles related to notable leaders and organizations

    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
    1:0.03
    2:0.09
    3:0.27
    4:0.02
    5:0.02
    6:0.11
    7:0.11
    8:0.05
    9:0.09
    10:0.07
    11:0.08
    Negative Logits
    ccording
    -1.34
    エル
    -1.19
    Newsletter
    -1.10
     cannabin
    -1.06
    rate
    -1.03
    VIDIA
    -1.02
     paralysis
    -0.99
     involuntary
    -0.99
     Rhythm
    -0.97
    Cap
    -0.95
    POSITIVE LOGITS
    ebook
    1.20
    roman
    1.20
    inton
    1.12
    alez
    1.11
    ayn
    1.11
    vati
    1.10
    ollar
    1.08
    agall
    1.07
    ondo
    1.07
    iano
    1.07
    Activations Density 0.009%

    No Known Activations