© 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. 2-ATT-KK
    11. 22087
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the concept of "very" in relation to notable moments or aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.03
    2:0.08
    3:0.10
    4:0.10
    5:0.12
    6:0.04
    7:0.02
    8:0.10
    9:0.19
    10:0.05
    11:0.03
    Negative Logits
     Thomson
    -1.49
    Cur
    -1.43
     Insight
    -1.37
    KR
    -1.29
     Landing
    -1.21
     Wong
    -1.21
     Frazier
    -1.20
     Lanka
    -1.18
    Builder
    -1.17
    uba
    -1.16
    POSITIVE LOGITS
    azo
    1.52
     fanbase
    1.48
    ulz
    1.48
     patriarchy
    1.44
    plets
    1.41
    ournal
    1.40
    osphere
    1.40
    est
    1.39
     thing
    1.38
     sphere
    1.36
    Activations Density 0.036%

    No Known Activations