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. 2-ATT-KK
    6. 22338
    Prev
    Next
    INDEX
    Explanations

    words associated with varying states of discomfort and struggle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.03
    2:0.33
    3:0.05
    4:0.09
    5:0.06
    6:0.03
    7:0.03
    8:0.08
    9:0.07
    10:0.05
    11:0.03
    Negative Logits
     Observatory
    -1.32
     occup
    -1.28
    aida
    -1.22
     occupation
    -1.19
    プ
    -1.18
     Balk
    -1.14
     Nost
    -1.14
     cutoff
    -1.05
     Maj
    -1.02
     operative
    -1.02
    POSITIVE LOGITS
    parts
    1.43
    puff
    1.34
    oslav
    1.33
    ombat
    1.27
    obin
    1.24
    nir
    1.21
    cycles
    1.20
    FACE
    1.17
    anon
    1.16
    pointer
    1.13
    Activations Density 0.004%

    No Known Activations