© 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. 25593
    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
    123
    +0.14
    0.8%
    457
    +0.12
    0.6%
    308
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.14
    0.45
    209
    +0.12
    0.29
    402
    +0.11
    0.26
    Negative Logits
    rectomy
    -1.72
    e
    -1.62
    duct
    -1.60
    eer
    -1.54
    ez
    -1.51
     sting
    -1.47
    erce
    -1.46
    actic
    -1.46
    ctrine
    -1.38
    onte
    -1.38
    POSITIVE LOGITS
    <|outofrange|>
    2.18
    2.18
    2.18
    2.18
    2.18
    ↵
    2.18
    ↵↵
    2.18
    2.18
    ↵
    2.18
    2.18
    Activations Density 1.569%

    No Known Activations

    This feature has no known activations.