© 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. 15362
    Prev
    Next
    INDEX
    Explanations

    the letter 'B' in isolation

    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
    0:0.08
    1:0.04
    2:0.07
    3:0.07
    4:0.08
    5:0.06
    6:0.18
    7:0.08
    8:0.08
    9:0.11
    10:0.03
    11:0.06
    Negative Logits
     Joe
    -3.97
     Joey
    -3.74
     José
    -3.70
     Teddy
    -3.62
    oj
    -3.54
    Joe
    -3.41
     Jed
    -3.39
     JO
    -3.32
     Roberto
    -3.27
    oa
    -3.27
    POSITIVE LOGITS
    Virgin
    3.51
    irgin
    3.19
    elsius
    3.10
    ysc
    2.96
    archment
    2.93
     tenants
    2.91
    adeon
    2.86
    rient
    2.82
    ority
    2.79
    Mesh
    2.75
    Activations Density 0.000%

    No Known Activations