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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 35712
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "to be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.03
    1:0.01
    2:0.06
    3:0.13
    4:0.08
    5:0.02
    6:0.15
    7:0.14
    8:0.04
    9:0.04
    10:0.15
    11:0.10
    Negative Logits
    tips
    -1.39
    research
    -1.34
    nothing
    -1.27
    urances
    -1.27
     Parables
    -1.26
    CRIPTION
    -1.23
    merce
    -1.23
    antage
    -1.23
    conduct
    -1.22
    uitive
    -1.20
    POSITIVE LOGITS
     persecut
    1.51
     CoC
    1.46
    ?",
    1.39
     attacker
    1.33
    alien
    1.31
     foe
    1.30
     GHz
    1.27
    atchewan
    1.25
     bigot
    1.25
     slug
    1.24
    Activations Density 0.010%

    No Known Activations