Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10549
    Prev
    Next
    INDEX
    Explanations

    time-related expressions or durations

    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
    0:0.03
    1:0.03
    2:0.12
    3:0.06
    4:0.02
    5:0.05
    6:0.08
    7:0.06
    8:0.12
    9:0.21
    10:0.10
    11:0.06
    Negative Logits
    stood
    -1.30
    ability
    -1.18
     sovereignty
    -1.11
     goodwill
    -1.08
    Tro
    -1.06
    Attack
    -1.05
     cohesion
    -1.04
    liners
    -1.00
    erity
    -0.99
    Balance
    -0.98
    POSITIVE LOGITS
    lyak
    1.39
     Moroc
    1.23
    schild
    1.18
     actionGroup
    1.08
    onym
    1.07
    ilk
    1.07
    href
    1.05
    ████
    1.04
     photograp
    1.04
     debunk
    1.03
    Activations Density 0.007%

    No Known Activations