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. 18886
    Prev
    Next
    INDEX
    Explanations

    terms related to government actions and their impacts on society

    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
    0:0.08
    1:0.03
    2:0.01
    3:0.07
    4:0.46
    5:0.06
    6:0.04
    7:0.03
    8:0.05
    9:0.07
    10:0.01
    11:0.02
    Negative Logits
    "))
    -2.62
    "),
    -2.31
    '),
    -2.18
     Participant
    -2.17
    ");
    -2.12
    ").
    -2.07
     ALL
    -2.07
    ').
    -2.06
     ACS
    -1.98
    ),"
    -1.89
    POSITIVE LOGITS
    fml
    2.21
    ucl
    2.21
    odan
    2.18
     ly
    2.05
     reckoning
    2.05
    ────
    2.05
    elsius
    2.04
     indifference
    1.95
    orns
    1.94
    uesday
    1.91
    Activations Density 0.018%

    No Known Activations