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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 27552
    Prev
    Next
    INDEX
    Explanations

    terms related to familial relationships and social roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.11
    1:0.14
    2:0.05
    3:0.09
    4:0.04
    5:0.18
    6:0.02
    7:0.02
    8:0.17
    9:0.06
    10:0.04
    11:0.03
    Negative Logits
    ="#
    -1.42
     suspected
    -1.40
     recalling
    -1.38
    dropping
    -1.36
    lig
    -1.36
    inous
    -1.30
     alleged
    -1.29
     claimed
    -1.27
    hetical
    -1.25
     disputed
    -1.25
    POSITIVE LOGITS
     …"
    2.08
     Indra
    1.90
     etc
    1.81
     …
    1.75
    ….
    1.64
    ,,,,
    1.61
    sic
    1.60
    ..."
    1.58
    …
    1.57
    …"
    1.55
    Activations Density 0.027%

    No Known Activations