© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27010
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ora", which could indicate a focus on a specific topic or section within the text

    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
    +0.13
    0.8%
    450
    +0.13
    0.7%
    283
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.13
    0.01
    450
    +0.13
    0.01
    385
    +0.12
    0.01
    Negative Logits
    ĥ½
    -2.11
    Īĺ
    -2.10
    ı
    -2.02
    ĵ
    -1.85
    Ĥ
    -1.84
    Ĥ¬
    -1.76
    IJ
    -1.73
    opy
    -1.67
    ij
    -1.66
    ľĵ
    -1.63
    POSITIVE LOGITS
    ÅĽci
    1.84
    lists
    1.84
    ptions
    1.77
    uscript
    1.72
    eries
    1.66
    ruptcy
    1.65
    enstein
    1.61
     rests
    1.60
    ios
    1.57
    ista
    1.55
    Activations Density 0.009%

    No Known Activations