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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 188
    Prev
    Next
    INDEX
    Explanations

    key descriptors related to the qualities of people and situations

    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
    0:0.03
    1:0.03
    2:0.07
    3:0.23
    4:0.03
    5:0.06
    6:0.02
    7:0.05
    8:0.02
    9:0.02
    10:0.36
    11:0.01
    Negative Logits
     planned
    -2.37
     developments
    -2.32
    Already
    -2.19
     plans
    -2.11
    idia
    -2.10
     woes
    -2.10
    isites
    -2.05
     obtained
    -2.02
     accrued
    -2.00
    ications
    -1.98
    POSITIVE LOGITS
     honest
    2.43
     accountable
    2.39
     truthful
    2.21
     disciplined
    2.20
     Silent
    2.11
     responsible
    2.01
     aware
    1.97
     unbiased
    1.96
     answ
    1.94
     respectful
    1.94
    Activations Density 0.107%

    No Known Activations