© 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. 25555
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to programming and process management

    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
    156
    +0.42
    2.5%
    232
    +0.10
    0.6%
    376
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    299
    +0.42
    0.07
    232
    +0.10
    0.11
    460
    +0.10
    0.06
    Negative Logits
    ambiguation
    -1.47
    forge
    -1.36
     quota
    -1.35
    Category
    -1.32
     abroad
    -1.32
    herty
    -1.28
     disadvantage
    -1.27
     lure
    -1.26
    Launch
    -1.25
    feas
    -1.24
    POSITIVE LOGITS
    ĻĤ
    3.21
    ¿½
    2.22
    ±
    2.04
    °
    1.99
    «
    1.99
    ¾
    1.93
    ¬
    1.86
    Į
    1.83
    Ļ
    1.82
    ģ
    1.81
    Activations Density 1.395%

    No Known Activations