© 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. 40749
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "I" indicating a first-person perspective

    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
    0:0.07
    1:0.07
    2:0.10
    3:0.08
    4:0.09
    5:0.07
    6:0.07
    7:0.10
    8:0.08
    9:0.06
    10:0.09
    11:0.08
    Negative Logits
     desirable
    -1.83
     generating
    -1.82
     microscopic
    -1.82
     proper
    -1.74
     narrowing
    -1.70
     Macron
    -1.68
     certain
    -1.63
     knockout
    -1.62
     cells
    -1.62
    AppData
    -1.60
    POSITIVE LOGITS
    sbm
    2.18
    andise
    1.89
    omaly
    1.88
    rike
    1.84
    YR
    1.83
    SHIP
    1.81
    alties
    1.80
    issance
    1.80
    itus
    1.79
    wagon
    1.73
    Activations Density 0.000%

    No Known Activations