© 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. 5-ATT-KK
    6. 43196
    Prev
    Next
    INDEX
    Explanations

    references to durations or specific periods

    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
    0:0.09
    1:0.06
    2:0.08
    3:0.07
    4:0.09
    5:0.08
    6:0.08
    7:0.07
    8:0.09
    9:0.06
    10:0.08
    11:0.07
    Negative Logits
     scrimmage
    -1.96
    ァ
    -1.83
     moderator
    -1.83
     weap
    -1.68
     distingu
    -1.67
    kef
    -1.63
    govtrack
    -1.62
     sil
    -1.61
     bloc
    -1.58
     civ
    -1.58
    POSITIVE LOGITS
    hovah
    1.80
     unsuccessful
    1.71
    osing
    1.69
    upt
    1.61
    Done
    1.60
    arden
    1.60
     wound
    1.58
    nova
    1.58
    ��
    1.53
    Winged
    1.53
    Activations Density 0.000%

    No Known Activations