© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 2984
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing comparison or contrast between different subjects or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.21
    2:0.03
    3:0.07
    4:0.06
    5:0.03
    6:0.03
    7:0.16
    8:0.03
    9:0.15
    10:0.10
    11:0.03
    Negative Logits
    ‎
    -2.55
    addin
    -2.50
    enegger
    -2.49
    656
    -2.43
    687
    -2.43
    779
    -2.43
    ovi
    -2.36
    768
    -2.32
     CAS
    -2.31
    visors
    -2.30
    POSITIVE LOGITS
    hhh
    2.68
    yip
    2.55
     Randolph
    2.47
    ��
    2.45
     sqor
    2.39
    pressed
    2.38
    Female
    2.37
    essage
    2.37
    hhhh
    2.36
    ural
    2.33
    Activations Density 0.000%

    No Known Activations