© 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. 31221
    Prev
    Next
    INDEX
    Explanations

    mentions of freedom or free services

    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
    355
    +0.13
    0.7%
    394
    +0.12
    0.7%
    97
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    355
    +0.13
    0.06
    170
    +0.12
    0.05
    394
    +0.11
    0.05
    Negative Logits
    edin
    -1.53
    chie
    -1.46
    ]>
    -1.44
     Missing
    -1.30
     Dun
    -1.29
     Million
    -1.26
     brow
    -1.25
     Driver
    -1.25
     Ske
    -1.24
    launchpad
    -1.24
    POSITIVE LOGITS
    ģ
    2.39
    Ī
    2.36
    Īĺ
    2.26
    µ
    2.11
    Ģ
    2.08
    <|outofrange|>
    1.99
    ↵↵↵
    1.99
    1.99
    č↵č↵
    1.99
    č↵
    1.99
    Activations Density 0.774%

    No Known Activations