© 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. 5-ATT-KK
    11. 43126
    Prev
    Next
    INDEX
    Explanations

    references to social media interactions explicitly mentioning users on Twitter or Facebook

    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
    0:0.02
    1:0.02
    2:0.04
    3:0.06
    4:0.09
    5:0.02
    6:0.07
    7:0.31
    8:0.04
    9:0.03
    10:0.11
    11:0.13
    Negative Logits
    otropic
    -1.69
    estate
    -1.55
     disadvant
    -1.51
     mism
    -1.49
     condos
    -1.49
    fact
    -1.48
     outnumbered
    -1.48
     depleted
    -1.38
    cedented
    -1.37
    pri
    -1.37
    POSITIVE LOGITS
     footsteps
    2.02
    hower
    1.48
     WATCH
    1.43
     Bastard
    1.42
     closely
    1.32
     Electronics
    1.32
    CLOSE
    1.31
    hetti
    1.29
     Pinball
    1.29
     Instruct
    1.28
    Activations Density 0.013%

    No Known Activations