© 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. 13604
    Prev
    Next
    INDEX
    Explanations

    specific names, numbers, and references within a narrative context

    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
    0:0.05
    1:0.39
    2:0.06
    3:0.07
    4:0.07
    5:0.04
    6:0.03
    7:0.07
    8:0.03
    9:0.03
    10:0.07
    11:0.04
    Negative Logits
    ocre
    -2.78
    seless
    -2.53
    iosyncr
    -2.43
    OUT
    -2.37
     ok
    -2.34
    ritic
    -2.33
    okin
    -2.27
    45
    -2.25
    akable
    -2.24
    42
    -2.21
    POSITIVE LOGITS
     had
    4.89
     hadn
    4.56
    had
    4.29
    Had
    4.22
     Had
    3.70
     retrospect
    3.04
    urion
    2.82
     regretted
    2.76
    having
    2.73
     subsequently
    2.68
    Activations Density 0.054%

    No Known Activations