© 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. 29404
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Little."

    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
    472
    +0.14
    0.8%
    338
    +0.13
    0.7%
    251
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    472
    +0.14
    0.02
    375
    +0.13
    0.02
    338
    +0.12
    0.02
    Negative Logits
    UTERS
    -1.80
    stant
    -1.75
    ĥ½
    -1.73
    shore
    -1.70
    olding
    -1.65
    REAM
    -1.62
    yon
    -1.56
     myself
    -1.53
    ĨĴ
    -1.51
    illance
    -1.46
    POSITIVE LOGITS
    istry
    1.55
     budgets
    1.54
    \$
    1.53
     sums
    1.52
     repetitions
    1.50
    forge
    1.49
     quantities
    1.48
     effort
    1.47
     combinations
    1.44
    ism
    1.43
    Activations Density 0.289%

    No Known Activations