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. 10165
    Prev
    Next
    INDEX
    Explanations

    occurrences 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
    0:0.32
    1:0.03
    2:0.06
    3:0.05
    4:0.09
    5:0.06
    6:0.06
    7:0.05
    8:0.06
    9:0.05
    10:0.07
    11:0.04
    Negative Logits
    Contents
    -1.54
    pmwiki
    -1.37
    occ
    -1.25
     ®
    -1.24
    SP
    -1.22
    icum
    -1.19
     &
    -1.14
    TM
    -1.14
    PR
    -1.14
    acc
    -1.09
    POSITIVE LOGITS
    merce
    1.56
    senal
    1.48
    etheless
    1.38
    ��
    1.37
     looph
    1.35
    �
    1.34
    �
    1.31
    �
    1.27
    �士
    1.26
    �
    1.25
    Activations Density 0.090%

    No Known Activations