© 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. 25961
    Prev
    Next
    INDEX
    Explanations

    the word "most" in various contexts

    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
    477
    +0.12
    0.7%
    433
    +0.12
    0.7%
    81
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    419
    +0.12
    0.01
    331
    +0.12
    0.02
    89
    +0.12
    0.01
    Negative Logits
    escent
    -1.90
     expiration
    -1.72
     itself
    -1.70
     altogether
    -1.68
    esso
    -1.59
     forever
    -1.56
    ±
    -1.53
     entirely
    -1.52
     mine
    -1.50
     theirs
    -1.50
    POSITIVE LOGITS
     Americans
    1.62
     Gospel
    1.47
    than
    1.40
    idden
    1.35
     Lik
    1.33
    rote
    1.33
    opoly
    1.33
    het
    1.29
    ák
    1.28
    izer
    1.28
    Activations Density 0.016%

    No Known Activations