© 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. 43234
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to economic metrics and analysis

    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
    0:0.03
    1:0.02
    2:0.36
    3:0.07
    4:0.07
    5:0.04
    6:0.07
    7:0.06
    8:0.06
    9:0.05
    10:0.07
    11:0.05
    Negative Logits
    sth
    -1.68
    �
    -1.56
    adow
    -1.55
    gard
    -1.45
    edom
    -1.40
     Shant
    -1.40
    ]}
    -1.38
    tsky
    -1.38
    HUD
    -1.35
    :]
    -1.33
    POSITIVE LOGITS
    accompan
    1.58
     extraord
    1.40
    esque
    1.39
     Ratio
    1.37
    imilar
    1.37
     Fever
    1.32
     Fra
    1.30
     rival
    1.26
     Fiat
    1.26
     ratio
    1.25
    Activations Density 0.131%

    No Known Activations