© 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. 26852
    Prev
    Next
    INDEX
    Explanations

    key terms related to tasks and operational 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
    408
    +0.12
    0.7%
    130
    +0.12
    0.7%
    358
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    189
    +0.12
    0.14
    130
    +0.12
    0.16
    465
    +0.12
    0.15
    Negative Logits
    ®
    -3.37
    ł
    -3.35
    ±
    -3.34
    ķ
    -3.30
    ³
    -3.25
    ¿½
    -3.17
    Ģ
    -3.15
    ²
    -3.11
    ¤
    -3.10
    IJ
    -3.09
    POSITIVE LOGITS
    à±ģ
    1.60
     affected
    1.58
    à³
    1.50
    à°¿
    1.48
    bank
    1.43
     constituency
    1.42
     sender
    1.42
    .."
    1.38
    à±į
    1.37
    "}](#
    1.35
    Activations Density 3.689%

    No Known Activations