© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43302
    Prev
    Next
    INDEX
    Explanations

    temporal references in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.01
    1:0.01
    2:0.08
    3:0.06
    4:0.16
    5:0.02
    6:0.07
    7:0.36
    8:0.03
    9:0.03
    10:0.05
    11:0.08
    Negative Logits
    etsy
    -1.44
     voices
    -1.35
     drums
    -1.30
     levers
    -1.29
    baugh
    -1.28
    emin
    -1.27
     abusive
    -1.23
     lashes
    -1.23
    bull
    -1.23
     rhetoric
    -1.22
    POSITIVE LOGITS
    ufact
    1.54
    Own
    1.54
     completion
    1.52
     fruition
    1.43
    Created
    1.38
    ynt
    1.35
     satisf
    1.33
    icipated
    1.32
     unden
    1.30
     Expend
    1.30
    Activations Density 0.004%

    No Known Activations