© 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. 27998
    Prev
    Next
    INDEX
    Explanations

    numerical values and their significance in context

    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
    445
    +0.14
    0.8%
    290
    +0.14
    0.8%
    258
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    445
    +0.14
    0.05
    307
    +0.14
    0.05
    290
    +0.12
    0.05
    Negative Logits
     mean
    -1.48
     difference
    -1.47
    rely
    -1.45
     capitalism
    -1.45
    arians
    -1.41
     doubt
    -1.39
     mere
    -1.39
     theory
    -1.37
    "?"
    -1.36
    opol
    -1.35
    POSITIVE LOGITS
    ¶
    2.81
    ¿½
    2.76
    ¥
    2.70
    ģ
    2.65
    Ĥ
    2.59
    ®
    2.55
    ĸ
    2.52
    º
    2.49
    Ĭ
    2.48
    ¬
    2.43
    Activations Density 0.172%

    No Known Activations