Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 44218
    Prev
    Next
    INDEX
    Explanations

    superlative adjectives and their applications in descriptions or rankings

    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
    0:0.26
    1:0.04
    2:0.10
    3:0.08
    4:0.06
    5:0.07
    6:0.04
    7:0.02
    8:0.08
    9:0.09
    10:0.06
    11:0.05
    Negative Logits
     hijacked
    -1.47
    miah
    -1.41
    idine
    -1.40
    dfx
    -1.37
     tagged
    -1.34
    TPPStreamerBot
    -1.33
     decided
    -1.32
    uy
    -1.31
     beet
    -1.30
    qqa
    -1.30
    POSITIVE LOGITS
     Favor
    2.17
     Appearance
    2.10
     Conduct
    1.85
     Influence
    1.82
     Hearing
    1.81
     Deaths
    1.79
    selves
    1.75
     Shows
    1.72
     Presence
    1.69
     Therapy
    1.69
    Activations Density 0.230%

    No Known Activations