© 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. 21890
    Prev
    Next
    INDEX
    Explanations

    instances of strong emotional expressions or sentiments related to frustration and disappointment

    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
    0:0.06
    1:0.04
    2:0.20
    3:0.11
    4:0.03
    5:0.10
    6:0.04
    7:0.03
    8:0.15
    9:0.10
    10:0.06
    11:0.03
    Negative Logits
    held
    -1.23
     guiActiveUnfocused
    -1.18
    arta
    -1.16
    quartered
    -1.14
    aminer
    -1.11
     Tracker
    -1.11
    ��
    -1.10
     Drawing
    -1.10
    interstitial
    -1.09
    riott
    -1.09
    POSITIVE LOGITS
    want
    1.19
    �
    1.17
    fy
    1.11
    OTE
    1.10
    DATA
    1.10
    phas
    1.10
    ּ
    1.08
    ALLY
    1.07
    NT
    1.07
     forgotten
    1.06
    Activations Density 0.047%

    No Known Activations