© 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. 28267
    Prev
    Next
    INDEX
    Explanations

    references to swinging and posture 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
    115
    +0.17
    1.0%
    376
    +0.16
    0.9%
    362
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    92
    +0.17
    0.01
    413
    +0.16
    0.01
    143
    +0.12
    0.01
    Negative Logits
    ¯
    -2.44
    «
    -2.02
    §
    -2.01
    ·
    -2.00
    ĥ½
    -1.97
    »¿
    -1.94
    ↵
    -1.88
    ↵↵
    -1.88
    ↵
    -1.88
    -1.88
    POSITIVE LOGITS
    wise
    2.15
    doms
    2.00
    able
    1.88
    ably
    1.79
     aside
    1.77
    keeping
    1.75
    bys
    1.65
    olecular
    1.57
    bugs
    1.56
    casting
    1.51
    Activations Density 3.574%

    No Known Activations