© 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. 26729
    Prev
    Next
    INDEX
    Explanations

    concepts related to programming or technical specifications

    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
    376
    +0.12
    0.6%
    32
    +0.11
    0.6%
    442
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    442
    +0.12
    0.05
    376
    +0.11
    0.04
    207
    +0.11
    0.04
    Negative Logits
     '</
    -1.57
    .'"
    -1.51
     deserve
    -1.40
    '."
    -1.38
     '$
    -1.33
    .'
    -1.33
     performed
    -1.28
    ''$
    -1.28
    oder
    -1.27
    ')$
    -1.26
    POSITIVE LOGITS
    ĻĤ
    2.65
    ĭ
    2.40
    ¤
    2.36
    ¿½
    2.30
    ±
    2.16
    ĨĴ
    2.12
    ª
    2.08
    ħ
    2.08
    ³
    2.08
    ł
    2.06
    Activations Density 0.128%

    No Known Activations