© 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. 29413
    Prev
    Next
    INDEX
    Explanations

    references to a specific name or term repeatedly mentioned in the text

    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
    144
    +0.15
    0.8%
    376
    +0.13
    0.7%
    467
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.15
    0.01
    144
    +0.13
    0.01
    467
    +0.12
    0.01
    Negative Logits
     thee
    -1.62
    ).](
    -1.56
     '')
    -1.52
     FIG
    -1.52
     poorer
    -1.44
     innocence
    -1.39
    ');
    -1.37
    ?’
    -1.37
     latter
    -1.37
     "")
    -1.36
    POSITIVE LOGITS
    emann
    1.98
    ű
    1.77
    estock
    1.74
    loop
    1.68
    stadt
    1.66
    acht
    1.63
    eman
    1.58
    iste
    1.55
    cav
    1.53
    isti
    1.52
    Activations Density 0.016%

    No Known Activations