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. 9254
    Prev
    Next
    INDEX
    Explanations

    instances of legal, social, and economic terminology related to rights and justice

    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
    0:0.05
    1:0.03
    2:0.01
    3:0.09
    4:0.50
    5:0.06
    6:0.03
    7:0.02
    8:0.06
    9:0.08
    10:0.01
    11:0.02
    Negative Logits
    ハ
    -2.83
    voc
    -2.18
    Í
    -2.14
    ::::
    -2.12
    .:
    -2.06
    aji
    -2.04
    apego
    -2.04
    :[
    -2.02
    ":
    -2.02
    taboola
    -2.02
    POSITIVE LOGITS
     overwhel
    2.27
     ensures
    2.10
    orate
    2.09
    did
    2.07
     does
    2.05
    raq
    2.03
     ensured
    2.01
    akedown
    2.00
     realise
    2.00
    idges
    1.99
    Activations Density 0.043%

    No Known Activations