© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 18853
    Prev
    Next
    INDEX
    Explanations

    assertions, claims, and discussions around controversial statements or events

    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
    0:0.10
    1:0.02
    2:0.37
    3:0.09
    4:0.04
    5:0.08
    6:0.02
    7:0.07
    8:0.03
    9:0.03
    10:0.08
    11:0.01
    Negative Logits
    Avoid
    -2.72
    limits
    -2.71
     condol
    -2.65
    duty
    -2.60
     reductions
    -2.56
    �醒
    -2.49
    avoid
    -2.40
     severity
    -2.39
     avoidance
    -2.37
     decency
    -2.34
    POSITIVE LOGITS
     genesis
    4.72
     founding
    3.98
     creation
    3.86
     incub
    3.80
     Invention
    3.79
     precursor
    3.67
     inception
    3.55
     Creation
    3.54
     invention
    3.52
     Origins
    3.51
    Activations Density 0.892%

    No Known Activations