© 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. 20776
    Prev
    Next
    INDEX
    Explanations

    references to risk and associated 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
    0:0.42
    1:0.01
    2:0.16
    3:0.07
    4:0.02
    5:0.05
    6:0.02
    7:0.04
    8:0.03
    9:0.02
    10:0.09
    11:0.02
    Negative Logits
     translator
    -2.62
     airing
    -2.44
     assembly
    -2.36
     compiling
    -2.34
     sewing
    -2.34
     editing
    -2.31
     primer
    -2.28
     phil
    -2.28
     lex
    -2.26
     ado
    -2.24
    POSITIVE LOGITS
     Risk
    3.09
     risks
    3.05
     mit
    2.80
     mitigation
    2.74
     risk
    2.61
    risk
    2.56
     horm
    2.50
     posed
    2.44
     borne
    2.40
    heit
    2.38
    Activations Density 0.031%

    No Known Activations