© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 25137
    Prev
    Next
    INDEX
    Explanations

    references to specific decades, particularly the 1930s and 1940s

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    44
    +0.13
    0.7%
    250
    +0.12
    0.7%
    100
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    7
    +0.13
    0.01
    82
    +0.12
    0.01
    44
    +0.12
    0.01
    Negative Logits
     suspicion
    -1.78
    wered
    -1.64
    ...](
    -1.64
     blame
    -1.52
    pired
    -1.48
     mere
    -1.47
    ard
    -1.46
     vengeance
    -1.45
     punishment
    -1.44
     remotely
    -1.43
    POSITIVE LOGITS
    ¿½
    2.34
    ĥ½
    2.34
    ®
    2.26
    ª
    2.18
    Ń
    2.17
    »
    2.10
    ģ
    2.09
    ł
    2.02
    ¬
    2.02
    ¥
    2.01
    Activations Density 0.011%

    No Known Activations