© 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 EvalsExportsAPI 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. 28790
    Prev
    Next
    INDEX
    Explanations

    references to a calendar in the document

    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
    156
    +0.13
    0.7%
    507
    +0.12
    0.7%
    376
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.13
    0.01
    507
    +0.12
    0.01
    110
    +0.10
    0.01
    Negative Logits
     themselves
    -1.81
    §
    -1.68
    ĵ
    -1.63
     spite
    -1.60
     rude
    -1.58
    ¯
    -1.54
     different
    -1.51
    ))$.
    -1.51
     happier
    -1.49
     queer
    -1.49
    POSITIVE LOGITS
    holder
    2.27
    nut
    2.04
    imetry
    1.96
    yard
    1.63
    uit
    1.62
    "}](#
    1.58
    kit
    1.58
    tube
    1.57
    imetric
    1.57
    rant
    1.57
    Activations Density 0.290%

    No Known Activations