© 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. 9-ATT-KK
    11. 3239
    Prev
    Next
    INDEX
    Explanations

    references to accidents and their consequences

    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
    0:0.05
    1:0.02
    2:0.06
    3:0.04
    4:0.05
    5:0.03
    6:0.18
    7:0.04
    8:0.06
    9:0.36
    10:0.03
    11:0.04
    Negative Logits
    bowl
    -4.66
     bowls
    -3.92
     bowl
    -3.41
    ogg
    -3.38
     saf
    -3.35
    poon
    -3.29
     Bowl
    -3.28
     Chic
    -3.20
     tab
    -3.09
    owl
    -3.08
    POSITIVE LOGITS
     Re
    6.71
     RE
    6.07
    Re
    6.05
     Rein
    5.61
     Kre
    5.58
    RE
    5.41
     Reilly
    5.13
     Rei
    5.13
    re
    5.09
     Ree
    5.07
    Activations Density 0.010%

    No Known Activations