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. 3-ATT-KK
    6. 7749
    Prev
    Next
    INDEX
    Explanations

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

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.02
    2:0.10
    3:0.16
    4:0.02
    5:0.02
    6:0.07
    7:0.19
    8:0.06
    9:0.03
    10:0.04
    11:0.21
    Negative Logits
    venants
    -1.63
    vable
    -1.55
    REE
    -1.50
    ree
    -1.41
    pared
    -1.39
    neau
    -1.38
    scribe
    -1.37
     alike
    -1.35
     wills
    -1.34
    leases
    -1.32
    POSITIVE LOGITS
    apo
    1.36
     assailant
    1.23
     missing
    1.21
     illeg
    1.20
    CVE
    1.19
     nationality
    1.19
     innocence
    1.15
     insign
    1.13
     badge
    1.13
     Identified
    1.10
    Activations Density 0.003%

    No Known Activations