© 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. 21937
    Prev
    Next
    INDEX
    Explanations

    terms related to product management and marketing strategies

    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
    0:0.03
    1:0.03
    2:0.28
    3:0.06
    4:0.06
    5:0.10
    6:0.02
    7:0.04
    8:0.04
    9:0.20
    10:0.06
    11:0.02
    Negative Logits
    っ
    -1.38
    notice
    -1.37
    anon
    -1.35
    ��
    -1.31
    repeat
    -1.26
    sbm
    -1.26
    dfx
    -1.23
    utsche
    -1.23
    hirt
    -1.22
    Sab
    -1.22
    POSITIVE LOGITS
     Consumers
    1.31
    terness
    1.30
     Jol
    1.24
    estyles
    1.24
    soever
    1.22
    arcity
    1.22
    ierrez
    1.21
     consumed
    1.17
    iaries
    1.15
    rities
    1.14
    Activations Density 0.032%

    No Known Activations