© 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. 40188
    Prev
    Next
    INDEX
    Explanations

    phrases involving the pronoun 'it' combined with verbs that indicate existence, action, or state

    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
    0:0.02
    1:0.01
    2:0.04
    3:0.06
    4:0.03
    5:0.14
    6:0.04
    7:0.03
    8:0.08
    9:0.09
    10:0.33
    11:0.07
    Negative Logits
    GROUP
    -1.80
     RS
    -1.74
     Luxem
    -1.67
     reservations
    -1.65
    NET
    -1.65
    essions
    -1.61
    GT
    -1.61
     superv
    -1.60
     squads
    -1.60
     NCT
    -1.59
    POSITIVE LOGITS
     odor
    1.97
     pudding
    1.81
     spores
    1.81
    worm
    1.81
     stain
    1.79
    Origin
    1.79
    facts
    1.78
     stains
    1.74
     smell
    1.73
     venom
    1.72
    Activations Density 0.390%

    No Known Activations