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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22355
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking issues seriously and emphasizing the need for actions or measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.01
    2:0.03
    3:0.06
    4:0.03
    5:0.05
    6:0.02
    7:0.07
    8:0.37
    9:0.04
    10:0.14
    11:0.07
    Negative Logits
    cci
    -1.44
    ndra
    -1.31
    alph
    -1.23
    bably
    -1.21
     agg
    -1.19
    fi
    -1.17
    ulty
    -1.16
     estates
    -1.15
    innie
    -1.13
    apo
    -1.10
    POSITIVE LOGITS
     seriously
    1.53
     aback
    1.45
     Seriously
    1.38
     lightly
    1.29
     hostage
    1.25
    BuyableInstoreAndOnline
    1.24
     Rez
    1.20
     ESV
    1.18
     offline
    1.15
    RESULTS
    1.14
    Activations Density 0.199%

    No Known Activations