© 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. 2-MLP-SM
    11. 26846
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter "n" 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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    156
    +0.23
    1.3%
    461
    +0.14
    0.8%
    290
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    50
    +0.23
    0.03
    261
    +0.14
    0.01
    461
    +0.13
    0.06
    Negative Logits
    ères
    -1.59
    Īĺ
    -1.47
    ometric
    -1.42
     ↵
    -1.41
    ↵
    -1.41
    ↵
    -1.41
    -1.41
    -1.41
    -1.41
    ↵↵
    -1.41
    POSITIVE LOGITS
    anie
    1.52
    ramble
    1.48
    aan
    1.46
    nonumber
    1.45
    aland
    1.41
    !--
    1.40
     DISCLAIM
    1.40
    're
    1.40
    де
    1.39
    ilight
    1.37
    Activations Density 1.133%

    No Known Activations