© 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. 2-MLP-SM
    11. 27116
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to metabolism and biochemical processes

    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
    +0.24
    1.4%
    263
    +0.13
    0.8%
    448
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.24
    0.06
    232
    +0.13
    0.08
    448
    +0.12
    0.04
    Negative Logits
    $–
    -1.84
     repertoire
    -1.74
     reperto
    -1.53
    aria
    -1.53
    versus
    -1.52
    +)
    -1.52
    ¶
    -1.51
    Īĺ
    -1.49
    -âĤ¬
    -1.48
    $-$
    -1.47
    POSITIVE LOGITS
     gent
    1.68
    us
    1.57
     wet
    1.57
     warm
    1.56
    usk
    1.55
     icy
    1.52
     moist
    1.52
     gentle
    1.52
    ustr
    1.48
    uty
    1.48
    Activations Density 0.624%

    No Known Activations