© 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. 25309
    Prev
    Next
    INDEX
    Explanations

    references to electric vehicles and electric power sources

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    111
    +0.13
    0.7%
    156
    +0.12
    0.7%
    2
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    331
    +0.13
    0.02
    491
    +0.12
    0.02
    111
    +0.12
    0.02
    Negative Logits
    ção
    -1.60
    ções
    -1.60
     dramatic
    -1.56
     Peninsula
    -1.52
    ego
    -1.52
     eventual
    -1.50
    wegian
    -1.45
     apologize
    -1.44
     gradual
    -1.44
     any
    -1.43
    POSITIVE LOGITS
    Ł
    2.69
    ¦
    2.39
    ¬
    2.18
    ²
    2.03
    ĻĤ
    1.96
    ĸ
    1.91
    ŀ
    1.88
    ĺ
    1.85
    £
    1.82
    ķ
    1.82
    Activations Density 0.077%

    No Known Activations