© 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. 27823
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly those related to percentages or ratings

    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
    156
    +0.17
    0.9%
    106
    +0.14
    0.8%
    369
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    458
    +0.17
    0.04
    106
    +0.14
    0.03
    436
    +0.14
    0.03
    Negative Logits
    NOTES
    -1.49
    OSS
    -1.47
    eur
    -1.44
     Providence
    -1.40
    owski
    -1.39
     League
    -1.38
    rail
    -1.38
    ielder
    -1.37
     responsibility
    -1.35
    keit
    -1.35
    POSITIVE LOGITS
    Ľ
    2.25
    ĭ
    2.22
    ³
    2.18
    ¶
    2.06
    Į
    2.04
    th
    2.03
    ģ
    2.02
    ħ
    1.96
    µ
    1.96
    ĺ
    1.91
    Activations Density 0.056%

    No Known Activations