© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 45443
    Prev
    Next
    INDEX
    Explanations

    expressions of frustration or defensiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.15
    1:0.10
    2:0.05
    3:0.06
    4:0.08
    5:0.11
    6:0.05
    7:0.04
    8:0.16
    9:0.06
    10:0.04
    11:0.04
    Negative Logits
    verning
    -1.50
     inherit
    -1.50
     inability
    -1.49
     depos
    -1.46
    ldom
    -1.45
     Guinness
    -1.45
    abases
    -1.45
    perty
    -1.44
     STATS
    -1.44
     Percentage
    -1.41
    POSITIVE LOGITS
    jam
    1.90
    cade
    1.89
    pod
    1.86
    ouver
    1.75
    radio
    1.63
    riot
    1.59
    icago
    1.56
    rb
    1.56
    Anth
    1.54
    Pitt
    1.54
    Activations Density 0.000%

    No Known Activations