© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 26486
    Prev
    Next
    INDEX
    Explanations

    references to "CO," indicating affiliations with companies or corporations

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    23
    +0.21
    1.2%
    394
    +0.10
    0.6%
    391
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.21
    0.02
    374
    +0.10
    0.01
    316
    +0.09
    0.03
    Negative Logits
    enez
    -2.11
    enos
    -2.03
    itol
    -1.87
    enne
    -1.86
    enant
    -1.80
    ière
    -1.73
    ienn
    -1.72
    ento
    -1.69
    ians
    -1.69
    ienne
    -1.68
    POSITIVE LOGITS
     pore
    1.46
    ths
    1.45
     [...]
    1.38
     Physical
    1.37
    ations
    1.36
     acute
    1.36
     thoughts
    1.36
     pathological
    1.35
     Majesty
    1.34
     seriously
    1.32
    Activations Density 0.297%

    No Known Activations