© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 28064
    Prev
    Next
    INDEX
    Explanations

    references to frameworks

    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
    +0.23
    1.4%
    376
    +0.19
    1.1%
    274
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    162
    +0.23
    0.01
    189
    +0.19
    0.01
    257
    +0.10
    0.01
    Negative Logits
    ureus
    -2.02
     pleasure
    -1.53
    >'
    -1.46
     wonders
    -1.45
     welcome
    -1.44
     Publ
    -1.42
    rd
    -1.41
     Commons
    -1.36
     copyrighted
    -1.35
     rhet
    -1.34
    POSITIVE LOGITS
     controls
    1.89
    cles
    1.72
    builder
    1.59
    casts
    1.55
    ALLOC
    1.55
    ically
    1.53
    erna
    1.53
    ICA
    1.52
    lique
    1.52
    guide
    1.49
    Activations Density 0.012%

    No Known Activations