© 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. 26807
    Prev
    Next
    INDEX
    Explanations

    references to the Bluemix platform and UTF encoding standards

    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
    373
    +0.11
    0.6%
    375
    +0.11
    0.6%
    111
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.11
    0.01
    370
    +0.11
    0.01
    375
    +0.10
    0.01
    Negative Logits
     ours
    -1.42
    lar
    -1.42
    äs
    -1.41
     slightest
    -1.40
     welcome
    -1.37
     protective
    -1.36
    cue
    -1.33
    lav
    -1.32
    ^*
    -1.31
    urs
    -1.30
    POSITIVE LOGITS
    estone
    2.38
    recht
    1.75
    estock
    1.74
    edo
    1.65
    ridge
    1.61
    ies
    1.59
    âĢij
    1.57
    ieux
    1.56
    pocket
    1.53
    ie
    1.51
    Activations Density 0.015%

    No Known Activations