Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 11470
    Prev
    Next
    INDEX
    Explanations

    instances of numerical data and ranking systems

    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
    0:0.03
    1:0.41
    2:0.02
    3:0.05
    4:0.06
    5:0.09
    6:0.07
    7:0.06
    8:0.02
    9:0.03
    10:0.03
    11:0.08
    Negative Logits
    sylv
    -2.98
     originals
    -2.96
     135
    -2.94
     134
    -2.86
     136
    -2.85
     1500
    -2.85
     XIII
    -2.83
     137
    -2.75
    stro
    -2.73
     1400
    -2.65
    POSITIVE LOGITS
    cz
    2.92
     c
    2.90
    cms
    2.81
    cue
    2.77
     cue
    2.67
    clave
    2.60
     C
    2.58
    urus
    2.55
    ‎
    2.52
     Cameroon
    2.47
    Activations Density 0.011%

    No Known Activations