© 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 EvalsExportsinterp-engineNEWAPI 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. 29764
    Prev
    Next
    INDEX
    Explanations

    references to pH and humidity levels

    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
    29
    +0.13
    0.7%
    71
    +0.13
    0.7%
    500
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    319
    +0.13
    0.01
    57
    +0.13
    0.01
    500
    +0.12
    0.01
    Negative Logits
    ¼
    -2.71
    ij
    -2.63
    IJ
    -2.53
    ¾
    -2.50
    Ŀ
    -2.48
    ³
    -2.43
    ĸ
    -2.38
    ´
    -2.38
    ±
    -2.36
    ¯
    -2.34
    POSITIVE LOGITS
    *****
    1.57
    ways
    1.56
    robe
    1.52
     situation
    1.51
     follows
    1.50
     Stadium
    1.48
    --------------------------------------------------------------------------------------------------------------------------------
    1.48
    rait
    1.48
    FC
    1.47
    fest
    1.45
    Activations Density 0.340%

    No Known Activations