© 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. 45437
    Prev
    Next
    INDEX
    Explanations

    instances of personal pronouns and subjective statements

    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
    2:0.05
    3:0.19
    4:0.11
    5:0.07
    6:0.11
    7:0.03
    8:0.03
    9:0.09
    10:0.05
    11:0.15
    Negative Logits
    Reloaded
    -1.72
    thouse
    -1.44
    ��
    -1.44
    CCC
    -1.41
    lap
    -1.32
    ACA
    -1.30
    Americ
    -1.30
    AAA
    -1.26
    AMA
    -1.24
    population
    -1.22
    POSITIVE LOGITS
    ommod
    1.48
     communicates
    1.23
     attribut
    1.22
    ecycle
    1.20
     initiation
    1.18
     fin
    1.16
     inappropriately
    1.16
     prey
    1.15
    ategor
    1.14
     distinction
    1.14
    Activations Density 0.036%

    No Known Activations