© 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. 8115
    Prev
    Next
    INDEX
    Explanations

    the presence of first-person pronouns and related personal expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.06
    1:0.05
    2:0.05
    3:0.05
    4:0.05
    5:0.14
    6:0.08
    7:0.01
    8:0.11
    9:0.13
    10:0.11
    11:0.10
    Negative Logits
     solicitation
    -1.16
    rament
    -1.15
    keeper
    -1.12
     advertis
    -1.12
    keepers
    -1.08
     Balt
    -1.08
     Harm
    -1.07
     Rain
    -1.07
    awks
    -1.07
    ction
    -1.05
    POSITIVE LOGITS
     loved
    1.42
    ��
    1.30
    enegger
    1.25
     dunno
    1.21
    alysed
    1.20
     Kardashian
    1.18
    self
    1.16
    tumblr
    1.15
    ______
    1.11
     detox
    1.11
    Activations Density 0.105%

    No Known Activations