Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 125
    Prev
    Next
    INDEX
    Explanations

    references to companionship or friendships

    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
    0:0.07
    1:0.09
    2:0.07
    3:0.07
    4:0.09
    5:0.08
    6:0.07
    7:0.09
    8:0.07
    9:0.08
    10:0.08
    11:0.07
    Negative Logits
    �
    -3.30
     Seym
    -3.10
    eki
    -2.96
    Sov
    -2.91
     Hok
    -2.84
    outheast
    -2.81
     McInt
    -2.80
     ath
    -2.72
     Quit
    -2.70
    ゴン
    -2.67
    POSITIVE LOGITS
     DEF
    3.19
     CASE
    3.04
     VIEW
    2.88
     CE
    2.76
     JUSTICE
    2.75
     Lex
    2.72
     Copyright
    2.72
     STAND
    2.70
     Views
    2.68
     AMERICA
    2.64
    Activations Density 0.000%

    No Known Activations