© 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. 27125
    Prev
    Next
    INDEX
    Explanations

    references to federations or confederations

    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
    +0.20
    1.2%
    461
    +0.13
    0.8%
    423
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    461
    +0.20
    0.01
    145
    +0.13
    0.01
    423
    +0.12
    0.01
    Negative Logits
     opposite
    -1.72
     somebody
    -1.68
     queer
    -1.67
     former
    -1.65
     behavioral
    -1.64
     faire
    -1.62
     teacher
    -1.61
     someone
    -1.61
     birth
    -1.59
    bbe
    -1.57
    POSITIVE LOGITS
    opan
    2.14
    ļ
    2.05
    ŀ
    2.02
    ĸ
    1.99
    ¡
    1.98
    ĭ
    1.96
    Ĺ
    1.93
    °
    1.87
    ¼
    1.84
    Ľ
    1.84
    Activations Density 0.227%

    No Known Activations