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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 28210
    Prev
    Next
    INDEX
    Explanations

    expressions of strong emotions, particularly frustration or distress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.09
    2:0.13
    3:0.07
    4:0.07
    5:0.11
    6:0.17
    7:0.03
    8:0.10
    9:0.04
    10:0.04
    11:0.06
    Negative Logits
     inclination
    -1.49
     exceptions
    -1.49
     circumstance
    -1.43
     slip
    -1.43
     contacts
    -1.41
     hers
    -1.34
     shrug
    -1.33
     follow
    -1.31
     splash
    -1.29
     curs
    -1.29
    POSITIVE LOGITS
    sbm
    1.85
    eco
    1.71
    iors
    1.66
    sty
    1.64
    tun
    1.62
    aquin
    1.57
    ashtra
    1.56
    Reviewer
    1.53
    rir
    1.52
    channelAvailability
    1.52
    Activations Density 0.000%

    No Known Activations