© 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. 10-ATT-KK
    11. 9717
    Prev
    Next
    INDEX
    Explanations

    instances of setbacks and the impact of individual actions on outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.02
    2:0.02
    3:0.04
    4:0.09
    5:0.52
    6:0.02
    7:0.04
    8:0.02
    9:0.11
    10:0.03
    11:0.03
    Negative Logits
    but
    -2.63
     Includes
    -2.62
     Expect
    -2.59
     Contains
    -2.59
     comprises
    -2.56
    }:
    -2.54
     Activities
    -2.50
     Include
    -2.48
     shall
    -2.47
    .;
    -2.44
    POSITIVE LOGITS
     refused
    4.85
     persisted
    4.69
    instead
    4.45
     didn
    4.33
    didn
    4.21
     instead
    4.13
     insisted
    4.08
     later
    4.01
     nonetheless
    3.88
     soon
    3.88
    Activations Density 0.834%

    No Known Activations