© 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. 2-ATT-KK
    11. 21983
    Prev
    Next
    INDEX
    Explanations

    instances of the word "stack" or related phrases suggesting accumulation or layering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.02
    2:0.20
    3:0.03
    4:0.29
    5:0.04
    6:0.02
    7:0.02
    8:0.07
    9:0.14
    10:0.04
    11:0.02
    Negative Logits
     Dhabi
    -1.31
     Baal
    -1.30
    gdala
    -1.29
    venge
    -1.26
     Promotion
    -1.25
     League
    -1.25
    speak
    -1.25
    ッド
    -1.24
    talk
    -1.21
    soever
    -1.20
    POSITIVE LOGITS
    eta
    1.53
    igham
    1.50
    ngth
    1.49
    pling
    1.47
    agos
    1.42
     folders
    1.41
    agall
    1.39
     shelves
    1.38
    ebted
    1.36
    bilt
    1.36
    Activations Density 0.004%

    No Known Activations