© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43182
    Prev
    Next
    INDEX
    Explanations

    complex philosophical arguments or critiques on societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    1:0.03
    2:0.07
    3:0.15
    4:0.07
    5:0.07
    6:0.03
    7:0.03
    8:0.10
    9:0.13
    10:0.19
    11:0.07
    Negative Logits
    ..............
    -1.51
    Reloaded
    -1.48
    Crew
    -1.43
    ................
    -1.29
    ..."
    -1.29
    ........
    -1.27
    Joined
    -1.26
    ,,,,
    -1.26
    .<
    -1.24
     [|
    -1.21
    POSITIVE LOGITS
     analogy
    1.60
     Debate
    1.46
     Understanding
    1.46
     Argument
    1.43
    argument
    1.41
     empir
    1.40
     debates
    1.37
    intuitive
    1.34
     theorists
    1.32
     debate
    1.31
    Activations Density 1.449%

    No Known Activations