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. 2974
    Prev
    Next
    INDEX
    Explanations

    references to decision-making and change in context of political or social issues

    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
    0:0.01
    1:0.01
    2:0.05
    3:0.04
    4:0.14
    5:0.02
    6:0.08
    7:0.44
    8:0.03
    9:0.03
    10:0.04
    11:0.06
    Negative Logits
    cade
    -1.86
    imentary
    -1.73
    dding
    -1.55
    Cru
    -1.54
    cour
    -1.52
    staking
    -1.50
    PLIED
    -1.47
    tips
    -1.47
    enary
    -1.41
    Dig
    -1.41
    POSITIVE LOGITS
     radically
    1.75
     fortunes
    1.70
     colours
    1.68
     drastically
    1.60
     colors
    1.57
     habits
    1.55
    tone
    1.53
     wording
    1.51
     dramatically
    1.49
     appearance
    1.48
    Activations Density 0.088%

    No Known Activations