© 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. 46581
    Prev
    Next
    INDEX
    Explanations

    occurrences of numerical information or significant symbols in the text

    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
    1:0.03
    2:0.08
    3:0.05
    4:0.10
    5:0.06
    6:0.03
    7:0.21
    8:0.05
    9:0.04
    10:0.15
    11:0.13
    Negative Logits
     coerc
    -1.97
    hra
    -1.76
     autonomy
    -1.74
     unilaterally
    -1.73
    agara
    -1.71
     waged
    -1.71
     firing
    -1.65
     sil
    -1.62
     exerted
    -1.62
    icide
    -1.59
    POSITIVE LOGITS
    livious
    2.09
    soType
    1.99
    ��
    1.74
     unden
    1.73
     Written
    1.70
    dayName
    1.68
    fters
    1.66
    ussen
    1.66
    amiliar
    1.64
     Presence
    1.63
    Activations Density 0.000%

    No Known Activations