© 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. 10488
    Prev
    Next
    INDEX
    Explanations

    words related to writing and creative expression

    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
    0:0.04
    1:0.39
    2:0.04
    3:0.06
    4:0.04
    5:0.04
    6:0.09
    7:0.04
    8:0.02
    9:0.11
    10:0.05
    11:0.03
    Negative Logits
     contradicts
    -2.71
    keys
    -2.69
     suggests
    -2.68
     alleges
    -2.66
     adds
    -2.40
     equivalents
    -2.38
     corresponds
    -2.37
    liest
    -2.35
     indicates
    -2.32
    kay
    -2.30
    POSITIVE LOGITS
     long
    5.42
     LONG
    5.09
    long
    4.06
    Long
    3.95
     Long
    3.49
     longer
    3.44
    cffffcc
    3.43
     externalToEVAOnly
    3.28
    ahime
    3.12
    ever
    3.11
    Activations Density 0.003%

    No Known Activations