© 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. 28360
    Prev
    Next
    INDEX
    Explanations

    instances of the word "each."

    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
    157
    +0.12
    0.6%
    204
    +0.11
    0.6%
    459
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    157
    +0.12
    0.09
    204
    +0.11
    0.07
    459
    +0.11
    0.06
    Negative Logits
     insulator
    -1.50
     altogether
    -1.40
     Pradesh
    -1.39
     equivalents
    -1.38
    omitempty
    -1.37
    igned
    -1.31
     conductors
    -1.31
     Arts
    -1.30
    ffff
    -1.28
     conductor
    -1.27
    POSITIVE LOGITS
     hereto
    2.11
    ?”
    1.77
    ?).
    1.77
    ?)
    1.75
    aliana
    1.71
    Affirmed
    1.60
     other
    1.60
    ”?
    1.55
     morning
    1.50
    ?’
    1.49
    Activations Density 3.705%

    No Known Activations