© 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 EvalsExportsinterp-engineNEWAPI 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. 29946
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "mil" indicating quantities related to millions

    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
    2
    +0.14
    0.8%
    111
    +0.14
    0.8%
    90
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    +0.14
    0.01
    90
    +0.14
    0.01
    111
    +0.12
    0.01
    Negative Logits
    emale
    -1.49
     yes
    -1.49
    omitempty
    -1.47
     nominal
    -1.46
     "âĻª
    -1.43
    ribut
    -1.42
    GREEK
    -1.42
    acting
    -1.41
     boolean
    -1.37
     fug
    -1.37
    POSITIVE LOGITS
    isecond
    1.80
    waukee
    1.78
    bridge
    1.76
    estones
    1.76
    ieux
    1.72
    ī
    1.71
    iseconds
    1.71
    enium
    1.65
    caster
    1.65
    ieu
    1.65
    Activations Density 0.121%

    No Known Activations