© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 26747
    Prev
    Next
    INDEX
    Explanations

    mentions of "ule" as part of product specifications or descriptions

    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
    376
    +0.14
    0.8%
    106
    +0.12
    0.7%
    467
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    293
    +0.14
    0.01
    106
    +0.12
    0.01
    64
    +0.12
    0.01
    Negative Logits
    '))
    -2.29
     ')
    -2.11
    '));
    -1.89
    '])
    -1.73
     ?"
    -1.66
     ");
    -1.66
     ")
    -1.66
    ']))
    -1.62
    '?"
    -1.61
    ...'
    -1.61
    POSITIVE LOGITS
    ¹
    3.27
    ↵
    3.18
    3.18
    ↵
    3.18
           ↵
    3.18
                  ↵
    3.18
    ↵            ↵
    3.18
    ↵
    3.18
    <|outofrange|>
    3.18
    ↵
    3.18
    Activations Density 0.396%

    No Known Activations