© 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. 29224
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    445
    +0.11
    0.6%
    351
    +0.11
    0.6%
    312
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.11
    0.48
    98
    +0.11
    0.21
    228
    +0.10
    0.32
    Negative Logits
    vester
    -1.91
    "."
    -1.76
    sic
    -1.64
    ]:
    -1.55
    "</
    -1.51
    aea
    -1.50
    ..."
    -1.48
    entary
    -1.48
    uration
    -1.48
    .""
    -1.48
    POSITIVE LOGITS
    Ĥ¬
    2.01
    ij
    1.99
    ¹
    1.94
    »
    1.90
    ¸
    1.73
    Ļ
    1.70
    Ļª
    1.69
    º
    1.69
    ¯
    1.61
    ĭ
    1.60
    Activations Density 2.913%

    No Known Activations

    This feature has no known activations.