© 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. 35837
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating possibility or ability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    1:0.01
    2:0.18
    3:0.12
    4:0.07
    5:0.03
    6:0.10
    7:0.13
    8:0.05
    9:0.07
    10:0.08
    11:0.07
    Negative Logits
    istries
    -1.45
    Rs
    -1.42
    ascus
    -1.25
    killing
    -1.22
    ylene
    -1.19
    agos
    -1.19
    emate
    -1.17
    chwitz
    -1.16
     fabrication
    -1.16
     whereabouts
    -1.14
    POSITIVE LOGITS
    multipl
    1.75
     attest
    1.41
    sequence
    1.40
     wont
    1.37
     *)
    1.33
    leader
    1.33
    >>\
    1.25
    uitive
    1.25
    FIG
    1.25
    oubted
    1.24
    Activations Density 0.007%

    No Known Activations