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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 43314
    Prev
    Next
    INDEX
    Explanations

    coordinating conjunctions and prepositions indicating relationships or connections between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.02
    2:0.06
    3:0.04
    4:0.11
    5:0.03
    6:0.36
    7:0.12
    8:0.03
    9:0.03
    10:0.07
    11:0.05
    Negative Logits
    forts
    -1.30
    ktop
    -1.18
    estic
    -1.18
    者
    -1.16
    phia
    -1.16
    venge
    -1.14
    ctors
    -1.13
    pron
    -1.12
    redients
    -1.12
    XM
    -1.10
    POSITIVE LOGITS
    EStream
    1.39
    sie
    1.35
    docker
    1.33
    ikuman
    1.29
     mirrors
    1.27
    istan
    1.26
     rails
    1.20
     tiss
    1.16
    thur
    1.14
     tails
    1.13
    Activations Density 0.033%

    No Known Activations