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

    Neuronpedia

    Jacobian LensNEW
    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. 45062
    Prev
    Next
    INDEX
    Explanations

    the word "since" and its contextual usage related to time or changes over a duration

    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
    1:0.01
    2:0.08
    3:0.11
    4:0.11
    5:0.02
    6:0.08
    7:0.06
    8:0.04
    9:0.03
    10:0.12
    11:0.28
    Negative Logits
    CVE
    -2.10
    skirts
    -1.84
    omaly
    -1.84
    achev
    -1.74
    apons
    -1.74
    olitics
    -1.72
    abus
    -1.67
    viol
    -1.62
    Memory
    -1.60
    suits
    -1.60
    POSITIVE LOGITS
     congrat
    1.90
    ��
    1.83
    hetti
    1.64
     congratulated
    1.63
    umers
    1.61
    代
    1.61
     thanking
    1.56
     subsid
    1.56
     congratulate
    1.55
    hower
    1.53
    Activations Density 0.001%

    No Known Activations