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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43907
    Prev
    Next
    INDEX
    Explanations

    temporal references and frequency of events

    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
    0:0.02
    1:0.02
    2:0.23
    3:0.11
    4:0.14
    5:0.03
    6:0.04
    7:0.11
    8:0.06
    9:0.03
    10:0.10
    11:0.07
    Negative Logits
    redo
    -1.70
    arde
    -1.65
    ako
    -1.61
    ACY
    -1.41
    osaurus
    -1.40
    icent
    -1.38
    ellation
    -1.38
    esta
    -1.33
    sonian
    -1.32
    �醒
    -1.29
    POSITIVE LOGITS
     consecut
    1.58
     outings
    1.57
     misconduct
    1.55
     attempted
    1.55
    Attempt
    1.41
     thefts
    1.35
     intermitt
    1.34
     visits
    1.32
     tried
    1.30
     incidents
    1.29
    Activations Density 0.058%

    No Known Activations