© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 18492
    Prev
    Next
    INDEX
    Explanations

    relationships or comparisons where something does not fit or belong

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.06
    2:0.08
    3:0.07
    4:0.08
    5:0.07
    6:0.06
    7:0.25
    8:0.04
    9:0.03
    10:0.09
    11:0.06
    Negative Logits
    they
    -3.67
     themselves
    -3.45
    their
    -3.43
     they
    -3.31
     theirs
    -3.26
    They
    -3.17
     Them
    -3.05
     their
    -3.03
     They
    -2.99
    Their
    -2.85
    POSITIVE LOGITS
    ntil
    2.52
    eport
    2.51
    �醒
    2.49
    ovember
    2.44
     裏�
    2.43
    ��
    2.40
    DAQ
    2.38
    ledged
    2.37
    ゴン
    2.31
    arde
    2.25
    Activations Density 0.000%

    No Known Activations