© 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. 5-ATT-KK
    11. 43097
    Prev
    Next
    INDEX
    Explanations

    the frequency of the word "to" and related phrases indicating actions or time references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.00
    2:0.26
    3:0.08
    4:0.16
    5:0.03
    6:0.05
    7:0.06
    8:0.03
    9:0.05
    10:0.12
    11:0.08
    Negative Logits
    appa
    -2.01
    �
    -1.82
    gow
    -1.76
    aughs
    -1.70
    �
    -1.65
    ��
    -1.54
    iewicz
    -1.50
    ��
    -1.50
    ISA
    -1.47
    SPONSORED
    -1.45
    POSITIVE LOGITS
     Siber
    1.42
    access
    1.40
     cf
    1.38
     seams
    1.34
     discont
    1.34
     fatig
    1.25
    !),
    1.25
    ').
    1.24
     access
    1.24
     unaccompanied
    1.24
    Activations Density 0.023%

    No Known Activations