© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 10494
    Prev
    Next
    INDEX
    Explanations

    references to discrediting individuals or claims, particularly in a critical context

    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
    0:0.06
    1:0.02
    2:0.05
    3:0.04
    4:0.06
    5:0.04
    6:0.26
    7:0.05
    8:0.08
    9:0.21
    10:0.04
    11:0.03
    Negative Logits
    enery
    -3.76
    anmar
    -3.68
    ctuary
    -3.56
     Foster
    -3.44
    orea
    -3.43
    Bridge
    -3.40
    isine
    -3.31
     Emerson
    -3.28
     Spur
    -3.25
    ouver
    -3.15
    POSITIVE LOGITS
     Kaz
    9.37
     Laz
    6.98
     Gaz
    5.84
     Baz
    5.77
     Yaz
    5.21
     Haz
    5.14
    az
    4.69
     Koz
    4.53
     Lazarus
    4.44
    tz
    4.25
    Activations Density 0.002%

    No Known Activations