© 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. 2-ATT-KK
    6. 22703
    Prev
    Next
    INDEX
    Explanations

    Adjectives

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

    instances of positional or directional movement within text

    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
    2:0.18
    3:0.06
    4:0.08
    5:0.07
    6:0.03
    7:0.02
    8:0.20
    9:0.14
    10:0.05
    11:0.03
    Negative Logits
    ascript
    -1.23
     disapp
    -1.22
     Cohn
    -1.13
     conclud
    -1.11
    SPONSORED
    -1.10
     repealed
    -1.07
     Warwick
    -1.07
    agically
    -1.05
    hof
    -1.03
     bookstore
    -1.02
    POSITIVE LOGITS
     裏�
    1.37
    unal
    1.34
     trough
    1.26
     seams
    1.22
    hair
    1.18
     Puzzles
    1.18
     Rin
    1.14
    uvian
    1.11
     externalToEVAOnly
    1.08
    wagen
    1.08
    Activations Density 0.006%

    No Known Activations