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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 18688
    Prev
    Next
    INDEX
    Explanations

    phrases expressing doubts or uncertainties regarding actions and intentions

    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
    0:0.06
    1:0.02
    2:0.06
    3:0.17
    4:0.03
    5:0.06
    6:0.02
    7:0.07
    8:0.03
    9:0.01
    10:0.40
    11:0.02
    Negative Logits
    checked
    -2.39
    quartered
    -2.14
    lished
    -2.14
    robat
    -2.13
     uniformly
    -2.12
     unfocusedRange
    -2.09
    Regular
    -2.04
    ailability
    -2.04
    stood
    -2.01
    lisher
    -1.99
    POSITIVE LOGITS
     Difference
    2.26
     Doing
    2.23
     versus
    2.21
     Saying
    2.14
     messing
    2.08
     Going
    1.98
     Effect
    1.96
     Changing
    1.94
     Effects
    1.93
     wrong
    1.93
    Activations Density 0.254%

    No Known Activations