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. 3-ATT-KK
    6. 9995
    Prev
    Next
    INDEX
    Explanations

    phrases indicating continuity and progression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.03
    2:0.05
    3:0.02
    4:0.01
    5:0.04
    6:0.03
    7:0.07
    8:0.05
    9:0.41
    10:0.05
    11:0.16
    Negative Logits
    dylib
    -1.33
    cu
    -1.23
     Surprise
    -1.17
    stood
    -1.14
     Barg
    -1.13
     Autism
    -1.13
     Fancy
    -1.12
     Chevy
    -1.09
     Too
    -1.07
    Runner
    -1.06
    POSITIVE LOGITS
    yrinth
    1.61
     indefinitely
    1.48
     faithfully
    1.47
     deterior
    1.43
     cautiously
    1.39
    jong
    1.37
     unchanged
    1.32
     steadily
    1.30
    Downloadha
    1.28
    hement
    1.28
    Activations Density 0.062%

    No Known Activations