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. 7-ATT-KK
    6. 18995
    Prev
    Next
    INDEX
    Explanations

    phrases about personal connections and interpersonal trust

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.05
    2:0.02
    3:0.08
    4:0.04
    5:0.07
    6:0.05
    7:0.04
    8:0.08
    9:0.37
    10:0.04
    11:0.02
    Negative Logits
     ILCS
    -2.16
     antioxid
    -1.98
     opio
    -1.82
    mun
    -1.82
    visor
    -1.82
    umper
    -1.80
    icipated
    -1.75
     Nationwide
    -1.75
     Tuls
    -1.73
    oxicity
    -1.72
    POSITIVE LOGITS
     simpler
    2.37
    swers
    1.96
     yeah
    1.90
    ichick
    1.88
     maybe
    1.87
     answer
    1.83
    UGH
    1.81
    actly
    1.78
     guesses
    1.76
     altogether
    1.75
    Activations Density 0.007%

    No Known Activations