© 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. 5-ATT-KK
    11. 43070
    Prev
    Next
    INDEX
    Explanations

    instances of specific characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.27
    1:0.03
    2:0.03
    3:0.07
    4:0.02
    5:0.07
    6:0.04
    7:0.01
    8:0.17
    9:0.11
    10:0.05
    11:0.06
    Negative Logits
     destro
    -1.68
     exha
    -1.62
     cumbers
    -1.54
     earthqu
    -1.50
     redundancy
    -1.50
     seiz
    -1.49
     separatist
    -1.46
     challeng
    -1.45
     tremend
    -1.43
     impe
    -1.41
    POSITIVE LOGITS
    .,
    2.12
    /,
    2.01
    ·
    1.98
    @
    1.88
    mc
    1.84
    ++
    1.83
    said
    1.74
    Advertisements
    1.74
    -.
    1.71
    ++)
    1.70
    Activations Density 0.040%

    No Known Activations