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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27796
    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
    460
    +0.12
    0.6%
    269
    +0.11
    0.6%
    484
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.12
    0.55
    56
    +0.11
    0.18
    203
    +0.11
    0.38
    Negative Logits
    ¨
    -2.40
    ¢
    -2.16
    Ľ
    -2.14
    ī
    -2.08
    atics
    -2.05
    Ń
    -2.01
    ¡
    -1.99
    ħ
    -1.92
    Ī
    -1.87
    ½
    -1.83
    POSITIVE LOGITS
    leted
    1.58
    lier
    1.52
    lichen
    1.52
    vast
    1.49
    orbit
    1.46
    anden
    1.43
    liest
    1.41
     suggestive
    1.38
    liche
    1.36
     arbitrary
    1.36
    Activations Density 3.561%

    No Known Activations

    This feature has no known activations.