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. 8382
    Prev
    Next
    INDEX
    Explanations

    phrases that describe responsibilities and expectations

    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
    3:0.10
    4:0.01
    5:0.04
    6:0.04
    7:0.07
    8:0.10
    9:0.30
    10:0.06
    11:0.09
    Negative Logits
    displayText
    -1.37
    earchers
    -1.36
    ":[{"
    -1.22
    ItemImage
    -1.19
    DragonMagazine
    -1.19
    ometer
    -1.17
    quickShipAvailable
    -1.16
    scient
    -1.13
     tends
    -1.13
    76561
    -1.12
    POSITIVE LOGITS
    ]}
    1.29
     Goodbye
    1.27
     Mata
    1.24
     Pai
    1.20
    verty
    1.16
    omen
    1.15
     Bye
    1.14
     Yose
    1.14
     Effective
    1.13
    HUD
    1.12
    Activations Density 0.002%

    No Known Activations