© 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. 37035
    Prev
    Next
    INDEX
    Explanations

    negative indicators and expressions of concern or caution

    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
    1:0.03
    2:0.06
    3:0.07
    4:0.10
    5:0.06
    6:0.24
    7:0.08
    8:0.07
    9:0.07
    10:0.06
    11:0.08
    Negative Logits
     uninterrupted
    -1.21
     catching
    -1.20
     sidel
    -1.17
    �
    -1.15
     urgent
    -1.12
     dysph
    -1.11
     dearly
    -1.10
     anx
    -1.08
     eagerly
    -1.08
    ORTS
    -1.07
    POSITIVE LOGITS
    ohm
    1.55
    dozen
    1.36
    ramids
    1.35
    rin
    1.35
    lights
    1.34
    abyte
    1.34
     sidx
    1.34
    roth
    1.33
    ctory
    1.32
    enium
    1.30
    Activations Density 0.000%

    No Known Activations