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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 22406
    Prev
    Next
    INDEX
    Explanations

    information related to technology and innovation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    statements that assert facts, truths, or realities, often in a scientific or analytical context

    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
    0:0.06
    1:0.04
    2:0.16
    3:0.14
    4:0.03
    5:0.06
    6:0.05
    7:0.06
    8:0.04
    9:0.11
    10:0.14
    11:0.05
    Negative Logits
    aucuses
    -1.33
    artney
    -1.32
     mosqu
    -1.24
    ategor
    -1.21
    ushima
    -1.20
     elig
    -1.20
    inia
    -1.15
    assies
    -1.13
     Camp
    -1.13
    osponsors
    -1.10
    POSITIVE LOGITS
    born
    1.34
     Argument
    1.25
    eenth
    1.22
     outweigh
    1.18
     element
    1.16
    argument
    1.16
    iest
    1.15
     inward
    1.12
     inherent
    1.12
    most
    1.11
    Activations Density 0.409%

    No Known Activations