© 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. 28211
    Prev
    Next
    INDEX
    Explanations

    the indefinite article "a"

    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
    23
    +0.30
    1.9%
    478
    +0.22
    1.4%
    98
    +0.21
    1.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    321
    +0.30
    0.24
    98
    +0.22
    0.15
    137
    +0.21
    0.25
    Negative Logits
    ÅĽci
    -1.93
    rails
    -1.72
    -1.71
    <|outofrange|>
    -1.71
    ↵
    -1.71
    <|outofrange|>
    -1.71
    č↵
    -1.71
    ↵
    -1.71
    -1.71
    č↵
    -1.71
    POSITIVE LOGITS
     few
    2.41
    usterity
    2.40
    cknowled
    2.29
     dozen
    2.22
     thousand
    2.15
     hundred
    2.12
     wider
    2.03
     lot
    2.02
     bunch
    1.97
     bit
    1.97
    Activations Density 1.270%

    No Known Activations