© 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. 28256
    Prev
    Next
    INDEX
    Explanations

    terms related to metadata standards and practices in library and information sciences

    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
    +0.14
    0.8%
    325
    +0.13
    0.7%
    409
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.14
    0.02
    156
    +0.13
    0.03
    79
    +0.10
    0.02
    Negative Logits
    ya
    -1.59
    enberg
    -1.57
    otom
    -1.53
    dered
    -1.52
    ayed
    -1.51
    ying
    -1.48
     goodbye
    -1.45
    idel
    -1.44
     farewell
    -1.43
    arial
    -1.43
    POSITIVE LOGITS
     annually
    1.55
    assadors
    1.43
    lot
    1.37
    head
    1.37
    orphism
    1.35
     every
    1.34
     Hour
    1.33
    "><
    1.30
    üt
    1.28
    üller
    1.27
    Activations Density 0.074%

    No Known Activations