© 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 EvalsExportsAPI 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. 28358
    Prev
    Next
    INDEX
    Explanations

    repeated patterns in data structures or formatting

    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
    119
    +0.12
    0.7%
    355
    +0.11
    0.6%
    150
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    495
    +0.12
    0.05
    35
    +0.11
    0.05
    421
    +0.11
    0.05
    Negative Logits
     responsibility
    -1.48
    terday
    -1.47
     day
    -1.44
    paced
    -1.40
    sized
    -1.37
     faced
    -1.35
     liability
    -1.34
     seed
    -1.33
     seeds
    -1.31
     ];
    -1.31
    POSITIVE LOGITS
    unch
    1.85
    ŀ
    1.71
    forth
    1.67
    hesis
    1.65
    Ī
    1.60
    Ł
    1.57
    ¬
    1.47
    illac
    1.44
    Ļª
    1.40
    ISM
    1.39
    Activations Density 0.064%

    No Known Activations