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. 5-ATT-KK
    6. 7278
    Prev
    Next
    INDEX
    Explanations

    names of notable individuals or figures, particularly focusing on Islamic leaders or personalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.02
    2:0.04
    3:0.06
    4:0.04
    5:0.04
    6:0.44
    7:0.05
    8:0.04
    9:0.06
    10:0.07
    11:0.06
    Negative Logits
    ngth
    -1.68
    ources
    -1.45
    BLIC
    -1.40
    inarily
    -1.30
     dilig
    -1.24
    emort
    -1.20
     JUSTICE
    -1.19
     agric
    -1.19
    idity
    -1.17
    incial
    -1.16
    POSITIVE LOGITS
    ー�
    1.48
    iru
    1.39
    chenko
    1.35
    ou
    1.32
    coni
    1.31
    roo
    1.28
    oud
    1.26
    oul
    1.26
    ミ
    1.25
     Barbie
    1.24
    Activations Density 0.003%

    No Known Activations