© 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. 37790
    Prev
    Next
    INDEX
    Explanations

    expressions of significant events or actions, particularly those involving heroism or critical responses to social issues

    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
    0:0.08
    1:0.02
    2:0.29
    3:0.04
    4:0.08
    5:0.03
    6:0.04
    7:0.05
    8:0.20
    9:0.02
    10:0.03
    11:0.06
    Negative Logits
    isters
    -1.70
    ories
    -1.69
    hesis
    -1.59
    orer
    -1.53
    orian
    -1.47
    zos
    -1.45
    Boot
    -1.45
    784
    -1.41
    chairs
    -1.40
    rimination
    -1.40
    POSITIVE LOGITS
     predec
    1.88
    ////////////////
    1.76
     respectively
    1.69
    agar
    1.56
    gemony
    1.55
    ahon
    1.54
    include
    1.49
    >"
    1.47
     overpowered
    1.46
    apult
    1.46
    Activations Density 0.036%

    No Known Activations