© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 28026
    Prev
    Next
    INDEX
    Explanations

    references to the act of being born

    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
    376
    +0.11
    0.6%
    246
    +0.11
    0.6%
    317
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    57
    +0.11
    0.02
    489
    +0.11
    0.02
    246
    +0.10
    0.02
    Negative Logits
    hed
    -1.59
    ```
    -1.58
    conduct
    -1.49
    ^](#
    -1.48
    unnumbered
    -1.43
     ease
    -1.41
    tox
    -1.41
    hydrox
    -1.39
    rfloor
    -1.38
     characterized
    -1.36
    POSITIVE LOGITS
    odynam
    1.54
    elta
    1.54
    jam
    1.51
    aña
    1.51
    fields
    1.51
     accelerator
    1.49
    etable
    1.48
    aje
    1.46
    vid
    1.45
     storage
    1.45
    Activations Density 0.374%

    No Known Activations