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. 18757
    Prev
    Next
    INDEX
    Explanations

    mentions of confinement or incarceration

    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
    0:0.11
    1:0.11
    2:0.08
    3:0.08
    4:0.04
    5:0.03
    6:0.08
    7:0.15
    8:0.06
    9:0.04
    10:0.07
    11:0.09
    Negative Logits
    dfx
    -1.96
    NK
    -1.95
    Nazis
    -1.92
    okia
    -1.85
    raq
    -1.84
    Naz
    -1.82
     automakers
    -1.79
     compromises
    -1.78
    oks
    -1.73
    ザ
    -1.73
    POSITIVE LOGITS
     Contribut
    2.28
     Lifetime
    2.07
     milestone
    2.02
     Candidate
    1.97
     Ranking
    1.95
     Maximum
    1.94
     Member
    1.94
     Potential
    1.91
     Ascension
    1.90
     Required
    1.90
    Activations Density 0.000%

    No Known Activations