Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 7-ATT-KK
    6. 9390
    Prev
    Next
    INDEX
    Explanations

    conjunctions and connective phrases that indicate relationships or logical connections between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.21
    1:0.05
    2:0.02
    3:0.05
    4:0.05
    5:0.04
    6:0.05
    7:0.10
    8:0.28
    9:0.06
    10:0.01
    11:0.02
    Negative Logits
     rake
    -1.71
    eele
    -1.59
     Roots
    -1.53
     parked
    -1.52
     nest
    -1.50
    ′
    -1.49
     booth
    -1.48
     poles
    -1.47
     silenced
    -1.42
     slams
    -1.41
    POSITIVE LOGITS
    ã
    2.16
    ivably
    2.10
    antically
    2.09
    NEWS
    2.03
    sbm
    1.84
    ombies
    1.75
    irtual
    1.75
    bly
    1.68
    roma
    1.67
    aline
    1.64
    Activations Density 0.001%

    No Known Activations