© 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. 9-ATT-KK
    11. 22524
    Prev
    Next
    INDEX
    Explanations

    the word "or" and related conjunctions that present alternatives or options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.33
    2:0.04
    3:0.10
    4:0.03
    5:0.07
    6:0.04
    7:0.05
    8:0.04
    9:0.05
    10:0.11
    11:0.05
    Negative Logits
     nonetheless
    -2.53
     nevertheless
    -2.44
     persists
    -2.34
     Danger
    -2.34
     beware
    -2.34
     equally
    -2.31
     someday
    -2.31
     never
    -2.26
    Adds
    -2.13
     unequ
    -2.12
    POSITIVE LOGITS
    umbn
    2.85
    igr
    2.63
    ught
    2.61
    aru
    2.59
    田
    2.56
    iman
    2.52
    ashi
    2.45
    okemon
    2.44
    覚醒
    2.42
    Last
    2.42
    Activations Density 0.001%

    No Known Activations