© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27665
    Prev
    Next
    INDEX
    Explanations

    the word "just" when it appears 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
    376
    +0.15
    0.8%
    241
    +0.13
    0.7%
    91
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    243
    +0.15
    0.03
    241
    +0.13
    0.03
    473
    +0.12
    0.03
    Negative Logits
    phrine
    -1.57
    athe
    -1.49
     best
    -1.44
    uclear
    -1.43
     brightest
    -1.39
     strongest
    -1.37
     life
    -1.33
     worst
    -1.31
     drugs
    -1.29
     relief
    -1.29
    POSITIVE LOGITS
    ifi
    1.88
    ices
    1.86
    ifiable
    1.75
    iom
    1.71
    isman
    1.70
    isma
    1.66
    IFY
    1.56
    ICES
    1.54
    ice
    1.53
    ified
    1.53
    Activations Density 0.143%

    No Known Activations