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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22300
    Prev
    Next
    INDEX
    Explanations

    pronouns and verbs indicating ongoing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.01
    2:0.22
    3:0.23
    4:0.06
    5:0.13
    6:0.01
    7:0.02
    8:0.11
    9:0.08
    10:0.03
    11:0.01
    Negative Logits
    י
    -1.34
    י�
    -1.26
     Recommend
    -1.23
     Rescue
    -1.22
     Message
    -1.18
     Ur
    -1.12
     Language
    -1.11
    Ur
    -1.08
     Wr
    -1.07
     Gram
    -1.06
    POSITIVE LOGITS
    anwhile
    1.56
    yip
    1.40
    nown
    1.40
    rily
    1.34
    phthal
    1.29
    ensibly
    1.26
     acknow
    1.26
    isSpecialOrderable
    1.25
    hyde
    1.23
     pretended
    1.21
    Activations Density 0.067%

    No Known Activations