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. 3-ATT-KK
    6. 8437
    Prev
    Next
    INDEX
    Explanations

    phrases reflecting individual perspectives and opinions

    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
    0:0.01
    1:0.06
    2:0.08
    3:0.03
    4:0.01
    5:0.07
    6:0.34
    7:0.06
    8:0.04
    9:0.04
    10:0.07
    11:0.12
    Negative Logits
     itself
    -1.13
    urrection
    -1.09
    cffffcc
    -1.09
     teasp
    -1.07
    catentry
    -1.05
     angered
    -1.04
    among
    -1.04
    intendent
    -1.03
    ourage
    -1.03
     signifies
    -1.02
    POSITIVE LOGITS
     congr
    1.35
     except
    1.30
     Clockwork
    1.22
     Dame
    1.14
     Lup
    1.06
     laughing
    1.04
     consensus
    1.00
    selves
    0.99
     agrees
    0.98
     toget
    0.96
    Activations Density 0.062%

    No Known Activations