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. 10157
    Prev
    Next
    INDEX
    Explanations

    statements about cultural and societal structures

    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
    0:0.08
    1:0.07
    2:0.08
    3:0.03
    4:0.09
    5:0.14
    6:0.07
    7:0.08
    8:0.06
    9:0.05
    10:0.14
    11:0.06
    Negative Logits
    edin
    -1.39
    装
    -1.29
    anticipated
    -1.21
     update
    -1.19
    early
    -1.15
    update
    -1.15
    cific
    -1.14
    iversary
    -1.13
     ][
    -1.10
     milestone
    -1.08
    POSITIVE LOGITS
     hemor
    1.33
     contrace
    1.32
     taxp
    1.30
     bye
    1.25
     democracies
    1.24
    merce
    1.22
     THEIR
    1.20
     Presbyter
    1.18
     domest
    1.18
     welf
    1.17
    Activations Density 0.814%

    No Known Activations