© 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. 27029
    Prev
    Next
    INDEX
    Explanations

    technical jargon related to programming and development

    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%
    478
    +0.13
    0.7%
    174
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.24
    0.09
    491
    +0.13
    0.06
    431
    +0.13
    0.07
    Negative Logits
    Inflater
    -1.62
    vez
    -1.59
    ships
    -1.55
    film
    -1.50
    ég
    -1.49
    films
    -1.48
     arrangement
    -1.47
    istas
    -1.46
     award
    -1.44
    ulsions
    -1.43
    POSITIVE LOGITS
     mine
    1.56
    idding
    1.56
    FROM
    1.55
    LLOW
    1.54
    ought
    1.53
    lesh
    1.53
     hers
    1.46
    FORE
    1.45
    OOK
    1.45
    bigr
    1.41
    Activations Density 2.363%

    No Known Activations