© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 28368
    Prev
    Next
    INDEX
    Explanations

    terms related to physical discomfort or pain

    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
    404
    +0.14
    0.8%
    376
    +0.12
    0.7%
    423
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    300
    +0.14
    0.01
    503
    +0.12
    0.01
    34
    +0.12
    0.01
    Negative Logits
     entirety
    -1.64
     entire
    -1.52
     aim
    -1.50
     latter
    -1.42
     question
    -1.36
     distant
    -1.33
     favor
    -1.31
     full
    -1.31
     houses
    -1.30
     directions
    -1.29
    POSITIVE LOGITS
    ¹
    3.07
    °
    2.71
    ±
    2.70
    ļ
    2.64
    ¸
    2.51
    µ
    2.50
    ĸ
    2.45
    £
    2.34
    ·
    2.32
    ²
    2.32
    Activations Density 0.007%

    No Known Activations