© 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. 43232
    Prev
    Next
    INDEX
    Explanations

    phrases related to expectations and assessments of performance or situations

    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
    0:0.02
    1:0.02
    2:0.09
    3:0.11
    4:0.46
    5:0.03
    6:0.04
    7:0.04
    8:0.02
    9:0.04
    10:0.04
    11:0.05
    Negative Logits
    nikov
    -1.93
    andering
    -1.68
    uning
    -1.62
     conspicuous
    -1.56
     menace
    -1.53
    achable
    -1.51
     interoper
    -1.49
    generated
    -1.42
    eness
    -1.42
    ilty
    -1.41
    POSITIVE LOGITS
     Grimm
    1.68
     Administ
    1.68
     Weiss
    1.55
    }}}
    1.51
     Coll
    1.47
     Ari
    1.46
     Schwarz
    1.44
     Kinder
    1.44
     Sapphire
    1.42
     Lindsay
    1.41
    Activations Density 0.042%

    No Known Activations