© 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. 21977
    Prev
    Next
    INDEX
    Explanations

    prepositions and their associations in 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
    1:0.02
    2:0.12
    3:0.05
    4:0.25
    5:0.04
    6:0.03
    7:0.02
    8:0.14
    9:0.14
    10:0.05
    11:0.02
    Negative Logits
     replaced
    -1.39
     repairs
    -1.32
     reluctantly
    -1.29
    BLIC
    -1.18
    escription
    -1.17
     refurb
    -1.16
     indemn
    -1.16
    Dur
    -1.14
    ooo
    -1.14
    vice
    -1.14
    POSITIVE LOGITS
    tones
    1.46
     patterns
    1.44
     similarities
    1.43
     Patterns
    1.40
     Attribution
    1.36
     unfocusedRange
    1.35
     happ
    1.35
     resemblance
    1.33
    MpServer
    1.32
    ulz
    1.31
    Activations Density 0.006%

    No Known Activations