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. 9425
    Prev
    Next
    INDEX
    Explanations

    personal pronouns

    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
    0:0.06
    1:0.06
    2:0.24
    3:0.04
    4:0.03
    5:0.04
    6:0.07
    7:0.08
    8:0.04
    9:0.04
    10:0.18
    11:0.09
    Negative Logits
     sshd
    -2.54
     '[
    -2.26
    oi
    -2.19
     Stall
    -2.15
    verages
    -2.01
     Lois
    -1.97
    ��
    -1.88
     Earthquake
    -1.88
     Polish
    -1.88
     Prel
    -1.87
    POSITIVE LOGITS
     browser
    2.45
    taboola
    2.36
     browsers
    2.26
    channelAvailability
    2.12
    displayText
    2.07
    ================================================================
    2.07
    isSpecialOrderable
    2.06
     unsupported
    2.06
     Currency
    2.04
     strapped
    2.02
    Activations Density 0.000%

    No Known Activations