© 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. 22584
    Prev
    Next
    INDEX
    Explanations

    statements about expectations and limitations

    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
    0:0.12
    1:0.02
    2:0.06
    3:0.05
    4:0.05
    5:0.03
    6:0.22
    7:0.05
    8:0.10
    9:0.21
    10:0.03
    11:0.02
    Negative Logits
    abor
    -4.17
     Maid
    -4.13
     Valiant
    -3.78
    Aid
    -3.62
    ected
    -3.43
     tent
    -3.39
    olkien
    -3.36
     encamp
    -3.26
    aid
    -3.26
    atu
    -3.25
    POSITIVE LOGITS
     Schro
    11.63
     Schr
    8.38
     Schl
    6.86
    Sch
    5.59
     Schwarz
    4.96
     Schultz
    4.60
    sch
    4.59
     Schw
    4.55
     Schwar
    4.46
     Schmidt
    4.39
    Activations Density 0.001%

    No Known Activations