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. 18685
    Prev
    Next
    INDEX
    Explanations

    references to authority figures or sources of information

    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
    0:0.07
    1:0.08
    2:0.08
    3:0.07
    4:0.08
    5:0.09
    6:0.08
    7:0.07
    8:0.09
    9:0.08
    10:0.08
    11:0.08
    Negative Logits
     Dome
    -2.95
     MPEG
    -2.88
     Rune
    -2.79
     Mania
    -2.72
     mm
    -2.71
     PLUS
    -2.67
     Meter
    -2.65
     Uz
    -2.61
     Boxing
    -2.61
     fuzz
    -2.57
    POSITIVE LOGITS
    quartered
    3.20
    rison
    2.87
    phas
    2.87
    orgetown
    2.82
     Carth
    2.76
    livious
    2.74
     Rebell
    2.73
    cknow
    2.73
    aghd
    2.70
    adelphia
    2.67
    Activations Density 0.000%

    No Known Activations