© 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. 2-MLP-SM
    6. 26932
    Prev
    Next
    INDEX
    Explanations

    references to authorship and licensing details in the text

    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
    9
    +0.12
    0.7%
    385
    +0.10
    0.6%
    446
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    380
    +0.12
    0.01
    385
    +0.10
    0.02
    497
    +0.10
    -0.00
    Negative Logits
    Director
    -1.63
     administrator
    -1.63
    ftware
    -1.58
    opsis
    -1.54
     compiled
    -1.49
     PUBL
    -1.45
     authority
    -1.43
     summarize
    -1.40
     Official
    -1.40
     interpreter
    -1.39
    POSITIVE LOGITS
    thy
    2.02
    icity
    1.66
    cyl
    1.65
    ickers
    1.55
    $]{}
    1.52
    tes
    1.51
    ocene
    1.41
    pes
    1.37
    urch
    1.37
    }$]{}
    1.37
    Activations Density 0.186%

    No Known Activations