Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9184
    Prev
    Next
    INDEX
    Explanations

    references to the themes of undercover operations and complex narratives in media

    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
    0:0.47
    1:0.02
    2:0.00
    3:0.02
    4:0.01
    5:0.22
    6:0.09
    7:0.03
    8:0.04
    9:0.02
    10:0.00
    11:0.01
    Negative Logits
    aturday
    -1.75
     preferred
    -1.75
    uces
    -1.71
     IPM
    -1.69
    eln
    -1.69
     decreased
    -1.67
     ceased
    -1.60
    astern
    -1.58
    mitter
    -1.57
    outer
    -1.57
    POSITIVE LOGITS
     Dreams
    2.02
     Chronicles
    1.80
     Heroes
    1.80
     Revelations
    1.78
     Tales
    1.74
     Reborn
    1.71
     Presents
    1.70
     Hitman
    1.69
     Avatar
    1.69
     Nightmares
    1.68
    Activations Density 0.002%

    No Known Activations