© 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. 2940
    Prev
    Next
    INDEX
    Explanations

    where a significant statement or conclusion is made, signified by a period

    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
    0:0.09
    1:0.07
    2:0.08
    3:0.09
    4:0.08
    5:0.08
    6:0.09
    7:0.08
    8:0.07
    9:0.07
    10:0.07
    11:0.07
    Negative Logits
    DIT
    -2.56
    letico
    -2.23
    bah
    -2.20
     ante
    -2.19
     Stat
    -2.17
     tot
    -2.13
     Fas
    -2.11
     Plat
    -2.11
     Electoral
    -2.10
    Apart
    -2.09
    POSITIVE LOGITS
    atform
    2.76
    iferation
    2.51
    ebted
    2.49
    ipples
    2.40
    ipple
    2.39
    iesel
    2.38
    assador
    2.35
    osponsors
    2.34
    ydia
    2.25
    isSpecialOrderable
    2.24
    Activations Density 0.000%

    No Known Activations