© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 22930
    Prev
    Next
    INDEX
    Explanations

    the presence of numerical references or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.10
    2:0.03
    3:0.09
    4:0.03
    5:0.12
    6:0.04
    7:0.12
    8:0.03
    9:0.12
    10:0.03
    11:0.21
    Negative Logits
     recognised
    -2.47
     *)
    -2.44
     isolation
    -2.44
     '[
    -2.36
     remote
    -2.29
     incap
    -2.22
     restrictive
    -2.21
     000
    -2.21
     guarantees
    -2.20
     arbitrarily
    -2.19
    POSITIVE LOGITS
    ラン
    2.65
    ニ
    2.64
    �
    2.63
    sbm
    2.62
    rentice
    2.59
    ーテ
    2.53
    ocaly
    2.51
     Dian
    2.48
    �
    2.47
    oston
    2.46
    Activations Density 0.003%

    No Known Activations