© 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. 3879
    Prev
    Next
    INDEX
    Explanations

    instances of the word "report" and related terms in various contexts, indicating a focus on reporting and journalism

    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
    2:0.14
    3:0.09
    4:0.18
    5:0.03
    6:0.05
    7:0.08
    8:0.04
    9:0.07
    10:0.08
    11:0.15
    Negative Logits
     migrant
    -1.25
     predators
    -1.24
    Downloadha
    -1.20
     burd
    -1.18
     behold
    -1.17
    grain
    -1.17
     killers
    -1.16
    borne
    -1.15
    ".[
    -1.15
    fer
    -1.14
    POSITIVE LOGITS
     Cheong
    1.49
    rieg
    1.38
    alde
    1.28
    umph
    1.27
    arcity
    1.24
    otaur
    1.23
    ichita
    1.23
     Cancel
    1.20
    ortium
    1.17
    Org
    1.17
    Activations Density 0.002%

    No Known Activations