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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 42819
    Prev
    Next
    INDEX
    Explanations

    exclamatory phrases or strong emphasis in the text

    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
    3:0.10
    4:0.28
    5:0.04
    6:0.10
    7:0.10
    8:0.04
    9:0.04
    10:0.06
    11:0.06
    Negative Logits
    ���
    -1.72
     meant
    -1.64
     owed
    -1.62
     incorrectly
    -1.60
     likened
    -1.55
     promotes
    -1.55
     existed
    -1.53
     acted
    -1.52
     outwe
    -1.51
     resembled
    -1.49
    POSITIVE LOGITS
    gettable
    1.49
     chronological
    1.46
    void
    1.43
    amaz
    1.42
    trace
    1.41
    gro
    1.41
    iosis
    1.40
     methodological
    1.39
     horizont
    1.37
     fruitful
    1.36
    Activations Density 0.000%

    No Known Activations