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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 7512
    Prev
    Next
    INDEX
    Explanations

    URLs associated with political content

    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
    0:0.04
    1:0.03
    2:0.16
    3:0.07
    4:0.09
    5:0.05
    6:0.09
    7:0.11
    8:0.03
    9:0.05
    10:0.15
    11:0.06
    Negative Logits
    ectomy
    -1.72
    rious
    -1.53
    aimon
    -1.52
    ivan
    -1.44
     counselors
    -1.41
    rieve
    -1.40
    ewitness
    -1.40
     warranties
    -1.38
    unctions
    -1.37
     reassure
    -1.35
    POSITIVE LOGITS
    establishment
    1.60
    govtrack
    1.59
     →
    1.58
    clinton
    1.52
    til
    1.40
     Elections
    1.40
    Republican
    1.36
     Opposition
    1.36
    politics
    1.35
     Democratic
    1.33
    Activations Density 0.000%

    No Known Activations