© 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. 2-ATT-KK
    6. 21984
    Prev
    Next
    INDEX
    Explanations

    specific names, titles, or designations

    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
    0:0.03
    1:0.03
    2:0.09
    3:0.14
    4:0.05
    5:0.11
    6:0.15
    7:0.04
    8:0.08
    9:0.09
    10:0.10
    11:0.04
    Negative Logits
     srfAttach
    -1.00
     Cull
    -0.76
     enclave
    -0.75
     foremost
    -0.75
     Prohibition
    -0.74
    ledged
    -0.73
     agre
    -0.72
     Clyde
    -0.71
     ware
    -0.71
     detachment
    -0.71
    POSITIVE LOGITS
    inav
    0.94
    Untitled
    0.94
    iq
    0.94
    borgh
    0.94
    yip
    0.93
    Synopsis
    0.93
    ernel
    0.88
    maxwell
    0.88
    gor
    0.85
    abo
    0.85
    Activations Density 0.092%

    No Known Activations