© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 46879
    Prev
    Next
    INDEX
    Explanations

    references to internal processes or states

    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
    1:0.01
    2:0.06
    3:0.05
    4:0.07
    5:0.02
    6:0.47
    7:0.08
    8:0.02
    9:0.03
    10:0.06
    11:0.05
    Negative Logits
    yip
    -1.83
    dinand
    -1.47
    ��
    -1.45
    bably
    -1.45
    uesday
    -1.44
    igmatic
    -1.43
    onne
    -1.43
    atsu
    -1.41
    ensitive
    -1.40
    bitious
    -1.38
    POSITIVE LOGITS
    ucl
    1.52
    GI
    1.25
    backer
    1.24
     gravity
    1.21
    advertisement
    1.19
    closure
    1.18
    herence
    1.17
    embed
    1.16
    asonry
    1.16
    cul
    1.15
    Activations Density 0.012%

    No Known Activations