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

    Neuronpedia

    Jacobian LensNEW
    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. 5-ATT-KK
    11. 41934
    Prev
    Next
    INDEX
    Explanations

    statements expressing beliefs or claims regarding the age of the Earth and religious faith

    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
    1:0.01
    2:0.17
    3:0.19
    4:0.14
    5:0.03
    6:0.02
    7:0.04
    8:0.06
    9:0.07
    10:0.13
    11:0.07
    Negative Logits
    ��
    -1.52
    mble
    -1.49
    undai
    -1.47
    azeera
    -1.37
    kered
    -1.37
    yssey
    -1.32
    idav
    -1.30
    urdue
    -1.30
    EEK
    -1.30
    ofi
    -1.30
    POSITIVE LOGITS
    ?",
    1.59
     Russians
    1.54
     equals
    1.53
     rapists
    1.52
    "?
    1.51
     blah
    1.51
     "…
    1.49
     Satanic
    1.45
     Jews
    1.45
     terrorists
    1.45
    Activations Density 1.375%

    No Known Activations