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. 44285
    Prev
    Next
    INDEX
    Explanations

    instances of political or social commentary on current events

    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
    0:0.04
    1:0.02
    2:0.09
    3:0.38
    4:0.06
    5:0.02
    6:0.02
    7:0.03
    8:0.05
    9:0.07
    10:0.08
    11:0.08
    Negative Logits
     millenn
    -2.01
    espie
    -1.91
     veter
    -1.84
     enthusi
    -1.76
    ahoo
    -1.75
     conflic
    -1.63
     snipp
    -1.63
    .")
    -1.62
    ModLoader
    -1.61
     psychiat
    -1.59
    POSITIVE LOGITS
    '?
    2.01
    )?
    1.93
     Edit
    1.88
    ?:
    1.77
    .--
    1.70
    ↵ 
    1.64
     ______
    1.61
     Born
    1.60
            
    1.60
    ベ
    1.59
    Activations Density 0.404%

    No Known Activations