© 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. 27858
    Prev
    Next
    INDEX
    Explanations

    instances of the word "arrival"

    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
    +0.15
    0.9%
    358
    +0.12
    0.7%
    455
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    455
    +0.15
    0.01
    358
    +0.12
    0.01
    347
    +0.11
    0.01
    Negative Logits
    §
    -1.95
    ĥ½
    -1.88
    ¹
    -1.85
    >&
    -1.70
    >\
    -1.69
    Į
    -1.68
    ³
    -1.66
    Ĥ¬
    -1.65
    >'
    -1.56
    Īĺ
    -1.55
    POSITIVE LOGITS
    endor
    1.90
     phase
    1.50
    aneous
    1.45
     modes
    1.45
    entially
    1.42
    less
    1.37
    burg
    1.37
    ulses
    1.37
    elles
    1.33
     signalling
    1.32
    Activations Density 0.080%

    No Known Activations