© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 43940
    Prev
    Next
    INDEX
    Explanations

    instances of the past tense verb "record."

    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
    0:0.07
    1:0.07
    2:0.09
    3:0.09
    4:0.07
    5:0.07
    6:0.10
    7:0.11
    8:0.06
    9:0.07
    10:0.08
    11:0.08
    Negative Logits
     Travels
    -1.75
     Sketch
    -1.69
     Contributions
    -1.62
    sections
    -1.60
     Discover
    -1.58
    section
    -1.56
     Chapters
    -1.54
     Journey
    -1.50
     Wrap
    -1.46
     Chin
    -1.46
    POSITIVE LOGITS
    omers
    1.96
    omorphic
    1.80
     constitu
    1.71
    umably
    1.67
     moratorium
    1.61
    ifference
    1.53
     lockdown
    1.52
    oult
    1.50
    rael
    1.48
    obyl
    1.47
    Activations Density 0.000%

    No Known Activations