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. 9618
    Prev
    Next
    INDEX
    Explanations

    concepts related to imitation and replication in various contexts

    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
    0:0.14
    1:0.05
    2:0.02
    3:0.13
    4:0.10
    5:0.13
    6:0.04
    7:0.01
    8:0.21
    9:0.10
    10:0.01
    11:0.02
    Negative Logits
     Leilan
    -1.99
    cember
    -1.90
    itives
    -1.88
     Investments
    -1.85
     Investig
    -1.84
    igun
    -1.79
     Advisory
    -1.77
    misc
    -1.70
     Payments
    -1.69
     Affect
    -1.64
    POSITIVE LOGITS
     beautifully
    1.97
     greatness
    1.94
     realism
    1.93
     dream
    1.92
     richness
    1.88
     creativity
    1.86
     classic
    1.86
     inventive
    1.84
     dens
    1.83
     vel
    1.83
    Activations Density 0.019%

    No Known Activations