© 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. 25503
    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
    3
    +0.14
    0.8%
    200
    +0.13
    0.7%
    314
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    41
    +0.14
    0.18
    473
    +0.13
    0.18
    266
    +0.12
    0.16
    Negative Logits
    ¿½
    -2.78
    §
    -2.58
    ĸ´
    -2.29
    Ĩ
    -2.24
    ¸
    -2.19
    «
    -2.18
    ħ
    -2.16
    ¡
    -2.16
    ļ
    -2.12
    ´
    -2.07
    POSITIVE LOGITS
    lash
    1.61
    cloth
    1.61
    âĪ¶
    1.45
    oder
    1.45
     whence
    1.44
    [@
    1.42
    ed
    1.40
    bage
    1.40
    ek
    1.38
    eds
    1.35
    Activations Density 0.399%

    No Known Activations

    This feature has no known activations.