© 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. 43189
    Prev
    Next
    INDEX
    Explanations

    clauses that express opinions or predictions

    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
    0:0.03
    1:0.03
    2:0.07
    3:0.31
    4:0.07
    5:0.07
    6:0.04
    7:0.03
    8:0.06
    9:0.11
    10:0.08
    11:0.05
    Negative Logits
    anwhile
    -1.57
    later
    -1.57
    quished
    -1.46
    �
    -1.43
     thereafter
    -1.42
    ゴン
    -1.40
    upon
    -1.34
     presumably
    -1.32
     later
    -1.31
     aloud
    -1.31
    POSITIVE LOGITS
    ,"
    2.97
    ),"
    2.92
    ..."
    2.83
    ,'"
    2.65
    ,''
    2.62
    )"
    2.60
    %"
    2.52
     …"
    2.50
    "
    2.45
    "))
    2.40
    Activations Density 0.415%

    No Known Activations