© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 11557
    Prev
    Next
    INDEX
    Explanations

    phrases indicating perseverance and overcoming challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.39
    2:0.06
    3:0.05
    4:0.04
    5:0.04
    6:0.06
    7:0.05
    8:0.02
    9:0.10
    10:0.07
    11:0.03
    Negative Logits
     il
    -2.79
    adj
    -2.75
    ultimate
    -2.71
    ible
    -2.66
    igl
    -2.62
    alph
    -2.56
    iam
    -2.55
    heimer
    -2.50
    oom
    -2.43
     initials
    -2.40
    POSITIVE LOGITS
    despite
    5.39
     despite
    5.13
     Despite
    4.11
    Despite
    4.00
     notwithstanding
    3.41
    raq
    3.23
     mirac
    3.08
     thankfully
    3.07
    azel
    3.06
     inexpl
    3.01
    Activations Density 0.002%

    No Known Activations