© 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. 26941
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "at" 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
    91
    +0.14
    0.8%
    363
    +0.12
    0.6%
    270
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    338
    +0.14
    0.08
    402
    +0.12
    0.07
    223
    +0.11
    0.06
    Negative Logits
    itude
    -1.69
    ings
    -1.66
    ness
    -1.63
    iversary
    -1.62
    ually
    -1.58
    ione
    -1.56
    eron
    -1.55
    ée
    -1.54
    eline
    -1.52
    iom
    -1.49
    POSITIVE LOGITS
    ¼
    2.82
    ĻĤ
    2.62
    ½
    2.38
    »
    2.38
    ª
    2.28
    Īĺ
    2.25
    Ĥ¬
    2.23
    ĵ
    2.23
    ĸ´
    2.23
    Ĭ
    2.14
    Activations Density 0.136%

    No Known Activations