© 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. 37897
    Prev
    Next
    INDEX
    Explanations

    negative sentiment or emotion

    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
    1:0.01
    2:0.06
    3:0.05
    4:0.03
    5:0.03
    6:0.44
    7:0.04
    8:0.05
    9:0.05
    10:0.06
    11:0.09
    Negative Logits
     unfocusedRange
    -1.40
    zb
    -1.35
    <?
    -1.28
    HOW
    -1.25
     Puzz
    -1.25
    adelphia
    -1.21
    ATIONAL
    -1.20
    20439
    -1.18
    inav
    -1.18
     fung
    -1.18
    POSITIVE LOGITS
    schild
    1.45
    inence
    1.25
    aunts
    1.24
    uber
    1.19
     dancer
    1.19
    ascal
    1.18
    ophile
    1.17
    inea
    1.17
    ress
    1.17
    î
    1.16
    Activations Density 0.019%

    No Known Activations