© 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. 43305
    Prev
    Next
    INDEX
    Explanations

    phrases indicating speech or quotation marks used in conversations

    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
    0:0.25
    1:0.13
    2:0.03
    3:0.04
    4:0.05
    5:0.06
    6:0.06
    7:0.05
    8:0.04
    9:0.06
    10:0.06
    11:0.11
    Negative Logits
    mas
    -1.63
    pb
    -1.61
    vind
    -1.60
    along
    -1.58
    odiac
    -1.55
    JV
    -1.53
    pun
    -1.51
    BBC
    -1.51
    indal
    -1.50
    zag
    -1.50
    POSITIVE LOGITS
     partName
    1.69
    76561
    1.67
     Goo
    1.64
    ccording
    1.64
    merce
    1.62
    >>\
    1.60
     appraisal
    1.58
    IUM
    1.58
    artment
    1.56
     DISTRICT
    1.54
    Activations Density 0.002%

    No Known Activations