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. 7572
    Prev
    Next
    INDEX
    Explanations

    references to political affiliations and party identifiers, particularly in the context of 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
    0:0.02
    1:0.02
    2:0.09
    3:0.06
    4:0.17
    5:0.03
    6:0.05
    7:0.28
    8:0.02
    9:0.04
    10:0.07
    11:0.09
    Negative Logits
    DEBUG
    -1.79
    FY
    -1.70
    Reviewer
    -1.59
    erity
    -1.59
    leave
    -1.57
     partName
    -1.56
    LEASE
    -1.53
    Scale
    -1.52
    IAS
    -1.48
    UTC
    -1.44
    POSITIVE LOGITS
    sov
    1.48
     Barnes
    1.47
     portfolio
    1.45
    auga
    1.35
     Lank
    1.32
     Chinatown
    1.32
     Lanka
    1.30
    oshenko
    1.29
     assemb
    1.28
     downt
    1.28
    Activations Density 0.000%

    No Known Activations