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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22336
    Prev
    Next
    INDEX
    Explanations

    comparisons and contrasts between different subjects or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.02
    2:0.24
    3:0.07
    4:0.11
    5:0.05
    6:0.02
    7:0.02
    8:0.19
    9:0.10
    10:0.04
    11:0.02
    Negative Logits
    guard
    -1.23
    RM
    -1.15
     Eater
    -1.15
    Reason
    -1.10
     bye
    -1.10
    Topics
    -1.09
    Assembly
    -1.08
     blocker
    -1.08
    /**
    -1.07
    Adds
    -1.07
    POSITIVE LOGITS
    MpServer
    1.72
    senal
    1.42
    ioxide
    1.39
    rast
    1.37
    quickShipAvailable
    1.34
    gage
    1.32
     favorably
    1.31
    soDeliveryDate
    1.30
    ilitary
    1.29
    imilar
    1.27
    Activations Density 0.008%

    No Known Activations