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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11385
    Prev
    Next
    INDEX
    Explanations

    logical connectors that indicate conditions or alternatives

    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
    1:0.16
    2:0.09
    3:0.07
    4:0.05
    5:0.11
    6:0.14
    7:0.15
    8:0.03
    9:0.03
    10:0.04
    11:0.03
    Negative Logits
     Temper
    -3.02
     tem
    -2.58
     Energy
    -2.57
     Centauri
    -2.52
     Chilean
    -2.36
     Chile
    -2.35
     Pound
    -2.35
     Rangers
    -2.32
     temperatures
    -2.24
     normally
    -2.24
    POSITIVE LOGITS
    ゴン
    3.08
    �
    2.83
    lie
    2.83
    soType
    2.81
    ahime
    2.80
    ウス
    2.63
    ertation
    2.59
    odox
    2.57
     omitted
    2.54
    lace
    2.50
    Activations Density 0.000%

    No Known Activations