© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 21860
    Prev
    Next
    INDEX
    Explanations

    recommendations and financial discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    2:0.05
    3:0.05
    4:0.03
    5:0.04
    6:0.10
    7:0.05
    8:0.04
    9:0.05
    10:0.08
    11:0.03
    Negative Logits
     bowed
    -2.18
    comb
    -2.06
     emoji
    -2.06
     Pun
    -2.04
     gag
    -2.00
     Afghans
    -1.97
     Abdel
    -1.97
     improvised
    -1.96
     Kaf
    -1.96
     brace
    -1.92
    POSITIVE LOGITS
    Reviewer
    2.48
    rypt
    2.43
     ASIC
    2.37
    join
    2.33
    �
    2.30
    Merit
    2.23
    tarians
    2.21
    onductor
    2.20
     dividend
    2.19
    tc
    2.16
    Activations Density 0.002%

    No Known Activations