© 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. 8408
    Prev
    Next
    INDEX
    Explanations

    references to neural signals and their implications in various contexts

    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
    0:0.10
    1:0.05
    2:0.08
    3:0.05
    4:0.05
    5:0.05
    6:0.14
    7:0.03
    8:0.03
    9:0.30
    10:0.04
    11:0.03
    Negative Logits
     Vac
    -3.56
     Epic
    -3.44
    ゴ
    -3.39
     Couch
    -3.29
     LEGO
    -3.25
    CU
    -3.18
     Kau
    -3.12
     Alz
    -2.98
     Lund
    -2.97
     Goldberg
    -2.95
    POSITIVE LOGITS
     signal
    6.97
     Signal
    6.82
     signals
    6.51
     signaling
    6.10
     signalling
    5.58
     signaled
    5.12
     Sign
    5.08
    sign
    4.96
    Sign
    4.68
     SIGN
    4.41
    Activations Density 0.002%

    No Known Activations