© 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. 44140
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "there" and its context in relation to presence, support, and action

    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
    2:0.12
    3:0.04
    4:0.13
    5:0.02
    6:0.02
    7:0.38
    8:0.03
    9:0.02
    10:0.07
    11:0.07
    Negative Logits
     seriousness
    -1.56
    acity
    -1.55
    anity
    -1.52
    inity
    -1.45
    prof
    -1.44
    iom
    -1.43
     prof
    -1.42
     understatement
    -1.39
     profess
    -1.38
    ionic
    -1.36
    POSITIVE LOGITS
    PsyNetMessage
    1.58
    wark
    1.49
     Lara
    1.44
     Greenwich
    1.43
    HCR
    1.35
    BOOK
    1.34
    apixel
    1.34
     landmarks
    1.33
     UID
    1.32
    arest
    1.32
    Activations Density 0.015%

    No Known Activations