Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 44166
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and references to actions or decisions

    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
    1:0.01
    2:0.23
    3:0.04
    4:0.18
    5:0.02
    6:0.13
    7:0.07
    8:0.10
    9:0.03
    10:0.05
    11:0.06
    Negative Logits
     PsyNet
    -1.65
     arrival
    -1.61
     Skydragon
    -1.58
    ading
    -1.49
    uers
    -1.48
    ewitness
    -1.43
    geries
    -1.32
    NetMessage
    -1.32
    rieved
    -1.32
    icious
    -1.30
    POSITIVE LOGITS
    ーク
    1.57
    aign
    1.39
    rast
    1.32
    bia
    1.32
    aline
    1.28
     prescribed
    1.23
     Fiorina
    1.22
    cpu
    1.19
    PLA
    1.17
     Costa
    1.16
    Activations Density 0.007%

    No Known Activations