© 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. 22037
    Prev
    Next
    INDEX
    Explanations

    expressions of criticism or observations about direction and purpose

    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
    0:0.04
    1:0.02
    2:0.12
    3:0.04
    4:0.31
    5:0.07
    6:0.03
    7:0.02
    8:0.09
    9:0.15
    10:0.04
    11:0.02
    Negative Logits
    owe
    -1.73
    raq
    -1.56
    oshenko
    -1.55
    iston
    -1.51
    pload
    -1.48
    abee
    -1.46
    ife
    -1.35
    CTV
    -1.34
    erb
    -1.30
    tle
    -1.28
    POSITIVE LOGITS
     direction
    1.57
     directions
    1.52
     directional
    1.39
    setting
    1.38
     latitude
    1.29
     interference
    1.29
     causation
    1.29
     navigation
    1.28
     altering
    1.27
     Direction
    1.27
    Activations Density 0.006%

    No Known Activations