© 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. 2-MLP-SM
    11. 25506
    Prev
    Next
    INDEX
    Explanations

    terms related to physiological processes and systems within the body

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    384
    +0.14
    0.8%
    127
    +0.12
    0.7%
    122
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    120
    +0.14
    0.07
    277
    +0.12
    0.06
    127
    +0.12
    0.07
    Negative Logits
     versus
    -1.51
    uper
    -1.50
    ahoma
    -1.48
    eto
    -1.47
    essions
    -1.37
    boro
    -1.36
    yma
    -1.36
     defeats
    -1.35
    rums
    -1.35
     respectively
    -1.34
    POSITIVE LOGITS
    lk
    1.40
    Enron
    1.37
     BGCOLOR
    1.33
    part
    1.32
     passengers
    1.32
    Decided
    1.31
     PUBL
    1.30
     constitu
    1.28
     Dame
    1.28
    >&
    1.27
    Activations Density 0.512%

    No Known Activations