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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9182
    Prev
    Next
    INDEX
    Explanations

    phrases conveying uncertainty and probability regarding future events

    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
    0:0.05
    1:0.05
    2:0.00
    3:0.08
    4:0.09
    5:0.05
    6:0.04
    7:0.02
    8:0.22
    9:0.31
    10:0.03
    11:0.01
    Negative Logits
     atmosphere
    -2.10
    itiz
    -1.93
     overload
    -1.91
     interactions
    -1.90
     interact
    -1.86
     blocker
    -1.84
    eware
    -1.79
    elight
    -1.78
    iban
    -1.78
     interacting
    -1.77
    POSITIVE LOGITS
    cember
    2.64
    )</
    2.63
    %);
    2.27
     anyway
    2.23
     YES
    2.21
    %)
    2.20
     yes
    2.18
    nr
    2.14
    )?
    2.04
    *)
    2.03
    Activations Density 0.031%

    No Known Activations