© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 8188
    Prev
    Next
    INDEX
    Explanations

    instances of strong emotions or reactions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.24
    1:0.05
    2:0.04
    3:0.06
    4:0.09
    5:0.07
    6:0.08
    7:0.03
    8:0.05
    9:0.04
    10:0.11
    11:0.08
    Negative Logits
    pmwiki
    -1.68
    Reloaded
    -1.42
    Technical
    -1.39
     Procedure
    -1.38
     Topic
    -1.38
    */(
    -1.34
    Detailed
    -1.34
     referen
    -1.29
     looph
    -1.23
     routines
    -1.19
    POSITIVE LOGITS
    acid
    1.67
    driving
    1.61
    pi
    1.59
    lund
    1.54
    lem
    1.52
    odes
    1.48
    anc
    1.47
    union
    1.41
    span
    1.37
    loss
    1.36
    Activations Density 0.003%

    No Known Activations