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. 5-ATT-KK
    6. 19150
    Prev
    Next
    INDEX
    Explanations

    temporal references and durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.01
    2:0.10
    3:0.17
    4:0.31
    5:0.02
    6:0.07
    7:0.09
    8:0.03
    9:0.03
    10:0.05
    11:0.04
    Negative Logits
    iven
    -1.58
    img
    -1.47
     fine
    -1.43
    .:
    -1.38
    .}
    -1.37
    fine
    -1.31
     ©
    -1.29
    itability
    -1.28
    +.
    -1.25
     mosa
    -1.24
    POSITIVE LOGITS
    actionDate
    1.52
    ptives
    1.43
    pires
    1.41
    Platform
    1.38
    itia
    1.37
    ativity
    1.35
    antage
    1.34
    Companies
    1.34
     awoke
    1.34
    ESA
    1.32
    Activations Density 0.043%

    No Known Activations