© 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. 28161
    Prev
    Next
    INDEX
    Explanations

    proper names and titles of individuals, often related to media or entertainment

    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
    0:0.02
    1:0.02
    2:0.05
    3:0.06
    4:0.04
    5:0.04
    6:0.33
    7:0.12
    8:0.05
    9:0.08
    10:0.09
    11:0.05
    Negative Logits
     facult
    -1.44
    worldly
    -1.36
    yip
    -1.30
    fml
    -1.27
    ificantly
    -1.23
    BLIC
    -1.17
    iable
    -1.15
    igible
    -1.13
     Dhabi
    -1.11
    ensibly
    -1.11
    POSITIVE LOGITS
    Bride
    1.36
     herself
    1.27
    rette
    1.26
    opol
    1.20
    xxx
    1.17
    ��
    1.16
    Jen
    1.14
    aminer
    1.14
    sch
    1.14
    pson
    1.13
    Activations Density 0.045%

    No Known Activations