© 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. 10545
    Prev
    Next
    INDEX
    Explanations

    answers to questions

    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
    0:0.04
    1:0.03
    2:0.04
    3:0.16
    4:0.05
    5:0.09
    6:0.03
    7:0.08
    8:0.03
    9:0.04
    10:0.04
    11:0.32
    Negative Logits
    ÃÂ
    -2.77
    etheless
    -2.68
    ÃÂÃÂ
    -2.59
     newcom
    -2.54
    �
    -2.49
    "},
    -2.47
    ccording
    -2.47
    '';
    -2.44
    ortunately
    -2.41
    !",
    -2.40
    POSITIVE LOGITS
    :
    3.90
     :
    2.23
    ...
    2.13
    …
    2.09
    CDC
    2.09
    cdn
    2.05
    :,
    2.05
    *:
    2.04
    Collins
    2.04
    cour
    1.97
    Activations Density 0.004%

    No Known Activations