© 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. 41601
    Prev
    Next
    INDEX
    Explanations

    phrases related to conversations or social interactions, particularly those that include action words

    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
    0:0.03
    1:0.02
    2:0.08
    3:0.06
    4:0.14
    5:0.03
    6:0.04
    7:0.37
    8:0.03
    9:0.04
    10:0.07
    11:0.04
    Negative Logits
    ヘ
    -2.06
    save
    -1.80
    pez
    -1.71
    insured
    -1.68
    pg
    -1.65
    geons
    -1.65
    keys
    -1.64
    imester
    -1.64
    externalActionCode
    -1.59
    zed
    -1.58
    POSITIVE LOGITS
     inconsistencies
    2.19
     discrepancies
    1.95
     hypotheses
    1.85
     flaws
    1.81
     contradictory
    1.79
     suspicion
    1.79
     suspicious
    1.78
     spurious
    1.78
     theories
    1.76
     inconsistency
    1.74
    Activations Density 0.000%

    No Known Activations