© 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. 30058
    Prev
    Next
    INDEX
    Explanations

    repeated occurrences of the number "14."

    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
    81
    +0.17
    1.0%
    458
    +0.13
    0.8%
    369
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.17
    0.03
    498
    +0.13
    0.03
    445
    +0.13
    0.03
    Negative Logits
    rition
    -1.75
    quier
    -1.61
    crow
    -1.56
     art
    -1.49
    eligible
    -1.46
    rica
    -1.45
     Wars
    -1.45
     genre
    -1.41
    geant
    -1.39
    catalina
    -1.37
    POSITIVE LOGITS
    ĥ½
    3.40
    ³
    3.15
    Ľ
    2.91
    Ń
    2.84
    ¾
    2.82
    ª
    2.82
    Į
    2.70
    ©
    2.64
    ł
    2.61
    ¬
    2.55
    Activations Density 0.019%

    No Known Activations