© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 22906
    Prev
    Next
    INDEX
    Explanations

    details related to news articles and events

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

    abbreviations and acronyms related to organizations and 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
    0:0.05
    1:0.03
    2:0.28
    3:0.06
    4:0.15
    5:0.05
    6:0.03
    7:0.03
    8:0.08
    9:0.11
    10:0.05
    11:0.03
    Negative Logits
    cause
    -1.34
    itch
    -1.27
    ksh
    -1.24
    itcher
    -1.17
    itching
    -1.16
    GHz
    -1.11
    itches
    -1.10
    Cause
    -1.07
    vention
    -1.07
    umbered
    -1.06
    POSITIVE LOGITS
    APTER
    1.55
    URA
    1.51
    Accessory
    1.38
    FUL
    1.34
    entin
    1.32
     conduc
    1.29
    TEXTURE
    1.28
    ccording
    1.24
    ENCY
    1.23
    WARE
    1.21
    Activations Density 0.011%

    No Known Activations