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. 9-ATT-KK
    6. 20665
    Prev
    Next
    INDEX
    Explanations

    references to efforts and actions related to political or social reforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.50
    1:0.01
    2:0.11
    3:0.07
    4:0.02
    5:0.03
    6:0.01
    7:0.05
    8:0.02
    9:0.02
    10:0.09
    11:0.01
    Negative Logits
     spoilers
    -2.99
     spoiler
    -2.51
     paraph
    -2.33
     lett
    -2.29
     seating
    -2.28
    OIL
    -2.27
     clauses
    -2.26
     indent
    -2.20
     certific
    -2.19
     prescribing
    -2.16
    POSITIVE LOGITS
     succeed
    3.30
     unsuccessful
    3.23
    ouble
    3.20
    successful
    3.18
     succeeded
    3.00
    successfully
    2.96
     futile
    2.78
     successes
    2.75
    �
    2.66
     Impossible
    2.60
    Activations Density 0.132%

    No Known Activations