© 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. 43296
    Prev
    Next
    INDEX
    Explanations

    expressions indicating time-related predictions or expectations

    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
    2:0.17
    3:0.05
    4:0.10
    5:0.09
    6:0.08
    7:0.05
    8:0.16
    9:0.04
    10:0.06
    11:0.09
    Negative Logits
    �醒
    -1.67
    ipel
    -1.61
    forts
    -1.49
    tyard
    -1.47
    itant
    -1.46
     basket
    -1.45
    andise
    -1.36
    apons
    -1.36
    ospital
    -1.36
    umbnails
    -1.34
    POSITIVE LOGITS
     depending
    1.65
    depending
    1.62
     MEP
    1.48
    morrow
    1.40
    Beg
    1.30
     Luigi
    1.27
     Enlight
    1.23
    DH
    1.23
     Abe
    1.23
     Die
    1.23
    Activations Density 0.001%

    No Known Activations